Search criteria
ⓘ
Use this form to refine search results.
Full-text search supports keyword queries with ranking and filtering.
You can combine vendor, product, and sources to narrow results.
Enable “Apply ordering” to sort by date instead of relevance.
34 vulnerabilities by langchain-ai
CVE-2026-41488 (GCVE-0-2026-41488)
Vulnerability from cvelistv5 – Published: 2026-04-24 20:57 – Updated: 2026-04-24 20:57
VLAI?
Title
angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding
Summary
LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch.
Severity ?
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
| URL | Tags | ||||
|---|---|---|---|---|---|
|
|||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-openai |
Affected:
< 1.1.14
|
{
"containers": {
"cna": {
"affected": [
{
"product": "langchain-openai",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 1.1.14"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai\u0027s _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 3.1,
"baseSeverity": "LOW",
"confidentialityImpact": "LOW",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-04-24T20:57:25.658Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r"
}
],
"source": {
"advisory": "GHSA-r7w7-9xr2-qq2r",
"discovery": "UNKNOWN"
},
"title": "angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-41488",
"datePublished": "2026-04-24T20:57:25.658Z",
"dateReserved": "2026-04-20T16:14:19.007Z",
"dateUpdated": "2026-04-24T20:57:25.658Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-41481 (GCVE-0-2026-41481)
Vulnerability from cvelistv5 – Published: 2026-04-24 20:54 – Updated: 2026-04-25 01:54
VLAI?
Title
LangChain: HTMLHeaderTextSplitter.split_text_from_url SSRF Redirect Bypass
Summary
LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters
1.1.2, HTMLHeaderTextSplitter.split_text_from_url() validated the initial URL using validate_safe_url() but then performed the fetch with requests.get() with redirects enabled (the default). Because redirect targets were not revalidated, a URL pointing to an attacker-controlled server could redirect to internal, localhost, or cloud metadata endpoints, bypassing SSRF protections. The response body is parsed and returned as Document objects to the calling application code. Whether this constitutes a data exfiltration path depends on the application: if it exposes Document contents (or derivatives) back to the requester who supplied the URL, sensitive data from internal endpoints could be leaked. Applications that store or process Documents internally without returning raw content to the requester are not directly exposed to data exfiltration through this issue. This vulnerability is fixed in 1.1.2.
Severity ?
6.5 (Medium)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
| URL | Tags | ||||
|---|---|---|---|---|---|
|
|||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-text-splitters |
Affected:
< 1.1.2
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-41481",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-04-25T01:54:07.352480Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-04-25T01:54:16.304Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain-text-splitters",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 1.1.2"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain is a framework for building agents and LLM-powered applications. Prior to langchain-text-splitters\n 1.1.2, HTMLHeaderTextSplitter.split_text_from_url() validated the initial URL using validate_safe_url() but then performed the fetch with requests.get() with redirects enabled (the default). Because redirect targets were not revalidated, a URL pointing to an attacker-controlled server could redirect to internal, localhost, or cloud metadata endpoints, bypassing SSRF protections. The response body is parsed and returned as Document objects to the calling application code. Whether this constitutes a data exfiltration path depends on the application: if it exposes Document contents (or derivatives) back to the requester who supplied the URL, sensitive data from internal endpoints could be leaked. Applications that store or process Documents internally without returning raw content to the requester are not directly exposed to data exfiltration through this issue. This vulnerability is fixed in 1.1.2."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-04-24T20:55:32.916Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-fv5p-p927-qmxr",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-fv5p-p927-qmxr"
}
],
"source": {
"advisory": "GHSA-fv5p-p927-qmxr",
"discovery": "UNKNOWN"
},
"title": "LangChain: HTMLHeaderTextSplitter.split_text_from_url SSRF Redirect Bypass"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-41481",
"datePublished": "2026-04-24T20:54:27.713Z",
"dateReserved": "2026-04-20T16:14:19.006Z",
"dateUpdated": "2026-04-25T01:54:16.304Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-41182 (GCVE-0-2026-41182)
Vulnerability from cvelistv5 – Published: 2026-04-23 00:14 – Updated: 2026-04-23 16:23
VLAI?
Title
LangSmith SDK: Streaming token events bypass output redaction
Summary
LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to version 0.5.19 of the JavaScript SDK and version 0.7.31 of the Python SDK, the LangSmith SDK's output redaction controls (hideOutputs in JS, hide_outputs in Python) do not apply to streaming token events. When an LLM run produces streaming output, each chunk is recorded as a new_token event containing the raw token value. These events bypass the redaction pipeline entirely — prepareRunCreateOrUpdateInputs (JS) and _hide_run_outputs (Python) only process the inputs and outputs fields on a run, never the events array. As a result, applications relying on output redaction to prevent sensitive LLM output from being stored in LangSmith will still leak the full streamed content via run events. Version 0.5.19 of the JavaScript SDK and version 0.7.31 of the Python SDK fix the issue.
Severity ?
5.3 (Medium)
CWE
Assigner
References
| URL | Tags | ||||
|---|---|---|---|---|---|
|
|||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langsmith-sdk |
Affected:
< 0.5.19
Affected: < 0.7.31 |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-41182",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-04-23T14:22:03.787610Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-04-23T16:23:39.037Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langsmith-sdk",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.5.19"
},
{
"status": "affected",
"version": "\u003c 0.7.31"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangSmith Client SDKs provide SDK\u0027s for interacting with the LangSmith platform. Prior to version 0.5.19 of the JavaScript SDK and version 0.7.31 of the Python SDK, the LangSmith SDK\u0027s output redaction controls (hideOutputs in JS, hide_outputs in Python) do not apply to streaming token events. When an LLM run produces streaming output, each chunk is recorded as a new_token event containing the raw token value. These events bypass the redaction pipeline entirely \u2014 prepareRunCreateOrUpdateInputs (JS) and _hide_run_outputs (Python) only process the inputs and outputs fields on a run, never the events array. As a result, applications relying on output redaction to prevent sensitive LLM output from being stored in LangSmith will still leak the full streamed content via run events. Version 0.5.19 of the JavaScript SDK and version 0.7.31 of the Python SDK fix the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 5.3,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-200",
"description": "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-359",
"description": "CWE-359: Exposure of Private Personal Information to an Unauthorized Actor",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-532",
"description": "CWE-532: Insertion of Sensitive Information into Log File",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-04-23T00:14:20.964Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-rr7j-v2q5-chgv",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-rr7j-v2q5-chgv"
}
],
"source": {
"advisory": "GHSA-rr7j-v2q5-chgv",
"discovery": "UNKNOWN"
},
"title": "LangSmith SDK: Streaming token events bypass output redaction"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-41182",
"datePublished": "2026-04-23T00:14:20.964Z",
"dateReserved": "2026-04-17T16:34:45.526Z",
"dateUpdated": "2026-04-23T16:23:39.037Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-40190 (GCVE-0-2026-40190)
Vulnerability from cvelistv5 – Published: 2026-04-10 19:47 – Updated: 2026-04-13 16:13
VLAI?
Title
LangSmith Client SDKs has Prototype Pollution in langsmith-sdk via Incomplete `__proto__` Guard in Internal lodash `set()`
Summary
LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to 0.5.18, the LangSmith JavaScript/TypeScript SDK (langsmith) contains an incomplete prototype pollution fix in its internally vendored lodash set() utility. The baseAssignValue() function only guards against the __proto__ key, but fails to prevent traversal via constructor.prototype. This allows an attacker who controls keys in data processed by the createAnonymizer() API to pollute Object.prototype, affecting all objects in the Node.js process. This vulnerability is fixed in 0.5.18.
Severity ?
5.6 (Medium)
CWE
- CWE-1321 - Improperly Controlled Modification of Object Prototype Attributes ('Prototype Pollution')
Assigner
References
| URL | Tags | ||||
|---|---|---|---|---|---|
|
|||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langsmith-sdk |
Affected:
< 0.5.18
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-40190",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-04-13T16:13:33.168377Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-04-13T16:13:45.532Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langsmith-sdk",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.5.18"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangSmith Client SDKs provide SDK\u0027s for interacting with the LangSmith platform. Prior to 0.5.18, the LangSmith JavaScript/TypeScript SDK (langsmith) contains an incomplete prototype pollution fix in its internally vendored lodash set() utility. The baseAssignValue() function only guards against the __proto__ key, but fails to prevent traversal via constructor.prototype. This allows an attacker who controls keys in data processed by the createAnonymizer() API to pollute Object.prototype, affecting all objects in the Node.js process. This vulnerability is fixed in 0.5.18."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 5.6,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-1321",
"description": "CWE-1321: Improperly Controlled Modification of Object Prototype Attributes (\u0027Prototype Pollution\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-04-10T19:47:57.642Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-fw9q-39r9-c252",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-fw9q-39r9-c252"
}
],
"source": {
"advisory": "GHSA-fw9q-39r9-c252",
"discovery": "UNKNOWN"
},
"title": "LangSmith Client SDKs has Prototype Pollution in langsmith-sdk via Incomplete `__proto__` Guard in Internal lodash `set()`"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-40190",
"datePublished": "2026-04-10T19:47:57.642Z",
"dateReserved": "2026-04-09T20:59:17.620Z",
"dateUpdated": "2026-04-13T16:13:45.532Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-40087 (GCVE-0-2026-40087)
Vulnerability from cvelistv5 – Published: 2026-04-09 19:34 – Updated: 2026-04-14 14:48
VLAI?
Title
LangChain has incomplete f-string validation in prompt templates
Summary
LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.84 and 1.2.28, LangChain's f-string prompt-template validation was incomplete in two respects. First, some prompt template classes accepted f-string templates and formatted them without enforcing the same attribute-access validation as PromptTemplate. In particular, DictPromptTemplate and ImagePromptTemplate could accept templates containing attribute access or indexing expressions and subsequently evaluate those expressions during formatting. Second, f-string validation based on parsed top-level field names did not reject nested replacement fields inside format specifiers. In this pattern, the nested replacement field appears in the format specifier rather than in the top-level field name. As a result, earlier validation based on parsed field names did not reject the template even though Python formatting would still attempt to resolve the nested expression at runtime. This vulnerability is fixed in 0.3.84 and 1.2.28.
Severity ?
5.3 (Medium)
CWE
- CWE-1336 - Improper Neutralization of Special Elements Used in a Template Engine
Assigner
References
| URL | Tags | ||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
|||||||||||||||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain |
Affected:
< 0.3.83
Affected: >= 1.0.0a1, < 1.2.28 |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-40087",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-04-14T14:47:52.978194Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-04-14T14:48:03.160Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.3.83"
},
{
"status": "affected",
"version": "\u003e= 1.0.0a1, \u003c 1.2.28"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.84 and 1.2.28, LangChain\u0027s f-string prompt-template validation was incomplete in two respects. First, some prompt template classes accepted f-string templates and formatted them without enforcing the same attribute-access validation as PromptTemplate. In particular, DictPromptTemplate and ImagePromptTemplate could accept templates containing attribute access or indexing expressions and subsequently evaluate those expressions during formatting. Second, f-string validation based on parsed top-level field names did not reject nested replacement fields inside format specifiers. In this pattern, the nested replacement field appears in the format specifier rather than in the top-level field name. As a result, earlier validation based on parsed field names did not reject the template even though Python formatting would still attempt to resolve the nested expression at runtime. This vulnerability is fixed in 0.3.84 and 1.2.28."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 5.3,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-1336",
"description": "CWE-1336: Improper Neutralization of Special Elements Used in a Template Engine",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-04-09T19:34:55.198Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-926x-3r5x-gfhw",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-926x-3r5x-gfhw"
},
{
"name": "https://github.com/langchain-ai/langchain/pull/36612",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/pull/36612"
},
{
"name": "https://github.com/langchain-ai/langchain/pull/36613",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/pull/36613"
},
{
"name": "https://github.com/langchain-ai/langchain/commit/6bab0ba3c12328008ddca3e0d54ff5a6151cd27b",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/commit/6bab0ba3c12328008ddca3e0d54ff5a6151cd27b"
},
{
"name": "https://github.com/langchain-ai/langchain/commit/af2ed47c6f008cdd551f3c0d87db3774c8dfe258",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/commit/af2ed47c6f008cdd551f3c0d87db3774c8dfe258"
},
{
"name": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.84",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.84"
},
{
"name": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.28",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.28"
}
],
"source": {
"advisory": "GHSA-926x-3r5x-gfhw",
"discovery": "UNKNOWN"
},
"title": "LangChain has incomplete f-string validation in prompt templates"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-40087",
"datePublished": "2026-04-09T19:34:55.198Z",
"dateReserved": "2026-04-09T00:39:12.206Z",
"dateUpdated": "2026-04-14T14:48:03.160Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-34070 (GCVE-0-2026-34070)
Vulnerability from cvelistv5 – Published: 2026-03-31 02:01 – Updated: 2026-03-31 18:04
VLAI?
Title
LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions
Summary
LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22.
Severity ?
7.5 (High)
CWE
- CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Assigner
References
| URL | Tags | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
|||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain |
Affected:
< 1.2.22
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-34070",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-31T15:17:33.597003Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-03-31T18:04:59.283Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 1.2.22"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples). This issue has been patched in version 1.2.22."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-03-31T02:01:49.320Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-qh6h-p6c9-ff54"
},
{
"name": "https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/commit/27add913474e01e33bededf4096151130ba0d47c"
},
{
"name": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.22"
}
],
"source": {
"advisory": "GHSA-qh6h-p6c9-ff54",
"discovery": "UNKNOWN"
},
"title": "LangChain Core has Path Traversal vulnerabilites in legacy `load_prompt` functions"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-34070",
"datePublished": "2026-03-31T02:01:49.320Z",
"dateReserved": "2026-03-25T16:21:40.867Z",
"dateUpdated": "2026-03-31T18:04:59.283Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-28277 (GCVE-0-2026-28277)
Vulnerability from cvelistv5 – Published: 2026-03-05 19:10 – Updated: 2026-03-06 18:04
VLAI?
Title
LangGraph: Unsafe msgpack deserialization in LangGraph checkpoint loading
Summary
LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In version 1.0.9 and prior, LangGraph checkpointers can load msgpack-encoded checkpoints that reconstruct Python objects during deserialization. If an attacker can modify checkpoint data in the backing store (for example, after a database compromise or other privileged write access to the persistence layer), they can potentially supply a crafted payload that triggers unsafe object reconstruction when the checkpoint is loaded. No known patch is public.
Severity ?
6.8 (Medium)
CWE
- CWE-502 - Deserialization of Untrusted Data
Assigner
References
| URL | Tags | ||||
|---|---|---|---|---|---|
|
|||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langgraph |
Affected:
<= 1.0.9
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-28277",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-06T18:04:22.963963Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-03-06T18:04:29.687Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langgraph",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c= 1.0.9"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In version 1.0.9 and prior, LangGraph checkpointers can load msgpack-encoded checkpoints that reconstruct Python objects during deserialization. If an attacker can modify checkpoint data in the backing store (for example, after a database compromise or other privileged write access to the persistence layer), they can potentially supply a crafted payload that triggers unsafe object reconstruction when the checkpoint is loaded. No known patch is public."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "ADJACENT_NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 6.8,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "HIGH",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:A/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502: Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-03-05T19:10:36.865Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-g48c-2wqr-h844",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-g48c-2wqr-h844"
}
],
"source": {
"advisory": "GHSA-g48c-2wqr-h844",
"discovery": "UNKNOWN"
},
"title": "LangGraph: Unsafe msgpack deserialization in LangGraph checkpoint loading"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-28277",
"datePublished": "2026-03-05T19:10:36.865Z",
"dateReserved": "2026-02-26T01:52:58.734Z",
"dateUpdated": "2026-03-06T18:04:29.687Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-25750 (GCVE-0-2026-25750)
Vulnerability from cvelistv5 – Published: 2026-03-04 21:58 – Updated: 2026-03-05 15:42
VLAI?
Title
LangSmith Studio has URL Parameter Injection Vulnerability that Enables Token Theft via Malicious baseUrl
Summary
Langchain Helm Charts are Helm charts for deploying Langchain applications on Kubernetes. Prior to langchain-ai/helm version 0.12.71, a URL parameter injection vulnerability existed in LangSmith Studio that could allow unauthorized access to user accounts through stolen authentication tokens. The vulnerability affected both LangSmith Cloud and self-hosted deployments. Authenticated LangSmith users who clicked on a specially crafted malicious link would have their bearer token, user ID, and workspace ID transmitted to an attacker-controlled server. With this stolen token, an attacker could impersonate the victim and access any LangSmith resources or perform any actions the user was authorized to perform within their workspace. The attack required social engineering (phishing, malicious links in emails or chat applications) to convince users to click the crafted URL. The stolen tokens expired after 5 minutes, though repeated attacks against the same user were possible if they could be convinced to click malicious links multiple times. The fix in version 0.12.71 implements validation requiring user-defined allowed origins for the baseUrl parameter, preventing tokens from being sent to unauthorized servers. No known workarounds are available. Self-hosted customers must upgrade to the patched version.
Severity ?
CWE
- CWE-74 - Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')
Assigner
References
| URL | Tags | ||||
|---|---|---|---|---|---|
|
|||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | helm |
Affected:
< 0.12.71
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-25750",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-05T15:39:31.562876Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-03-05T15:42:21.213Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "helm",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.12.71"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "Langchain Helm Charts are Helm charts for deploying Langchain applications on Kubernetes. Prior to langchain-ai/helm version 0.12.71, a URL parameter injection vulnerability existed in LangSmith Studio that could allow unauthorized access to user accounts through stolen authentication tokens. The vulnerability affected both LangSmith Cloud and self-hosted deployments. Authenticated LangSmith users who clicked on a specially crafted malicious link would have their bearer token, user ID, and workspace ID transmitted to an attacker-controlled server. With this stolen token, an attacker could impersonate the victim and access any LangSmith resources or perform any actions the user was authorized to perform within their workspace. The attack required social engineering (phishing, malicious links in emails or chat applications) to convince users to click the crafted URL. The stolen tokens expired after 5 minutes, though repeated attacks against the same user were possible if they could be convinced to click malicious links multiple times. The fix in version 0.12.71 implements validation requiring user-defined allowed origins for the baseUrl parameter, preventing tokens from being sent to unauthorized servers. No known workarounds are available. Self-hosted customers must upgrade to the patched version."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.5,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "ACTIVE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-74",
"description": "CWE-74: Improper Neutralization of Special Elements in Output Used by a Downstream Component (\u0027Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-03-04T21:58:59.119Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/helm/security/advisories/GHSA-r8wq-jwgw-p74g",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/helm/security/advisories/GHSA-r8wq-jwgw-p74g"
}
],
"source": {
"advisory": "GHSA-r8wq-jwgw-p74g",
"discovery": "UNKNOWN"
},
"title": "LangSmith Studio has URL Parameter Injection Vulnerability that Enables Token Theft via Malicious baseUrl"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-25750",
"datePublished": "2026-03-04T21:58:59.119Z",
"dateReserved": "2026-02-05T18:35:52.356Z",
"dateUpdated": "2026-03-05T15:42:21.213Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-27795 (GCVE-0-2026-27795)
Vulnerability from cvelistv5 – Published: 2026-02-25 17:30 – Updated: 2026-02-25 18:42
VLAI?
Title
LangChain Community: redirect chaining can lead to SSRF bypass via RecursiveUrlLoader
Summary
LangChain is a framework for building LLM-powered applications. Prior to version 1.1.8, a redirect-based Server-Side Request Forgery (SSRF) bypass exists in `RecursiveUrlLoader` in `@langchain/community`. The loader validates the initial URL but allows the underlying fetch to follow redirects automatically, which permits a transition from a safe public URL to an internal or metadata endpoint without revalidation. This is a bypass of the SSRF protections introduced in 1.1.14 (CVE-2026-26019). Users should upgrade to `@langchain/community` 1.1.18, which validates every redirect hop by disabling automatic redirects and re-validating `Location` targets before following them. In this version, automatic redirects are disabled (`redirect: "manual"`), each 3xx `Location` is resolved and validated with `validateSafeUrl()` before the next request, and a maximum redirect limit prevents infinite loops.
Severity ?
4.1 (Medium)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
| URL | Tags | ||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
|||||||||||||||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchainjs |
Affected:
< 1.1.18
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-27795",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-02-25T18:42:34.609541Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-02-25T18:42:52.277Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchainjs",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 1.1.18"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain is a framework for building LLM-powered applications. Prior to version 1.1.8, a redirect-based Server-Side Request Forgery (SSRF) bypass exists in `RecursiveUrlLoader` in `@langchain/community`. The loader validates the initial URL but allows the underlying fetch to follow redirects automatically, which permits a transition from a safe public URL to an internal or metadata endpoint without revalidation. This is a bypass of the SSRF protections introduced in 1.1.14 (CVE-2026-26019). Users should upgrade to `@langchain/community` 1.1.18, which validates every redirect hop by disabling automatic redirects and re-validating `Location` targets before following them. In this version, automatic redirects are disabled (`redirect: \"manual\"`), each 3xx `Location` is resolved and validated with `validateSafeUrl()` before the next request, and a maximum redirect limit prevents infinite loops."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 4.1,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:L/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-02-25T17:30:01.106Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-mphv-75cg-56wg",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-mphv-75cg-56wg"
},
{
"name": "https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-gf3v-fwqg-4vh7",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-gf3v-fwqg-4vh7"
},
{
"name": "https://github.com/langchain-ai/langchainjs/pull/9990",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/pull/9990"
},
{
"name": "https://github.com/langchain-ai/langchainjs/commit/2812d2b2b9fd9343c4850e2ab906b8cf440975ee",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/commit/2812d2b2b9fd9343c4850e2ab906b8cf440975ee"
},
{
"name": "https://github.com/langchain-ai/langchainjs/commit/d5e3db0d01ab321ec70a875805b2f74aefdadf9d",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/commit/d5e3db0d01ab321ec70a875805b2f74aefdadf9d"
},
{
"name": "https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcommunity%401.1.14",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcommunity%401.1.14"
},
{
"name": "https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcommunity%401.1.18",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcommunity%401.1.18"
}
],
"source": {
"advisory": "GHSA-mphv-75cg-56wg",
"discovery": "UNKNOWN"
},
"title": "LangChain Community: redirect chaining can lead to SSRF bypass via RecursiveUrlLoader"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-27795",
"datePublished": "2026-02-25T17:30:01.106Z",
"dateReserved": "2026-02-24T02:31:33.265Z",
"dateUpdated": "2026-02-25T18:42:52.277Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-27794 (GCVE-0-2026-27794)
Vulnerability from cvelistv5 – Published: 2026-02-25 16:53 – Updated: 2026-02-25 21:00
VLAI?
Title
LangGraph: BaseCache Deserialization of Untrusted Data may lead to Remote Code Execution
Summary
LangGraph Checkpoint defines the base interface for LangGraph checkpointers. Prior to version 4.0.0, a Remote Code Execution vulnerability exists in LangGraph's caching layer when applications enable cache backends that inherit from `BaseCache` and opt nodes into caching via `CachePolicy`. Prior to `langgraph-checkpoint` 4.0.0, `BaseCache` defaults to `JsonPlusSerializer(pickle_fallback=True)`. When msgpack serialization fails, cached values can be deserialized via `pickle.loads(...)`. Caching is not enabled by default. Applications are affected only when the application explicitly enables a cache backend (for example by passing `cache=...` to `StateGraph.compile(...)` or otherwise configuring a `BaseCache` implementation), one or more nodes opt into caching via `CachePolicy`, and the attacker can write to the cache backend (for example a network-accessible Redis instance with weak/no auth, shared cache infrastructure reachable by other tenants/services, or a writable SQLite cache file). An attacker must be able to write attacker-controlled bytes into the cache backend such that the LangGraph process later reads and deserializes them. This typically requires write access to a networked cache (for example a network-accessible Redis instance with weak/no auth or shared cache infrastructure reachable by other tenants/services) or write access to local cache storage (for example a writable SQLite cache file via permissive file permissions or a shared writable volume). Because exploitation requires write access to the cache storage layer, this is a post-compromise / post-access escalation vector. LangGraph Checkpoint 4.0.0 patches the issue.
Severity ?
6.6 (Medium)
CWE
- CWE-502 - Deserialization of Untrusted Data
Assigner
References
| URL | Tags | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langgraph-checkpoint |
Affected:
< 4.0.0
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-27794",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-02-25T21:00:12.555344Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-02-25T21:00:24.430Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langgraph-checkpoint",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 4.0.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangGraph Checkpoint defines the base interface for LangGraph checkpointers. Prior to version 4.0.0, a Remote Code Execution vulnerability exists in LangGraph\u0027s caching layer when applications enable cache backends that inherit from `BaseCache` and opt nodes into caching via `CachePolicy`. Prior to `langgraph-checkpoint` 4.0.0, `BaseCache` defaults to `JsonPlusSerializer(pickle_fallback=True)`. When msgpack serialization fails, cached values can be deserialized via `pickle.loads(...)`. Caching is not enabled by default. Applications are affected only when the application explicitly enables a cache backend (for example by passing `cache=...` to `StateGraph.compile(...)` or otherwise configuring a `BaseCache` implementation), one or more nodes opt into caching via `CachePolicy`, and the attacker can write to the cache backend (for example a network-accessible Redis instance with weak/no auth, shared cache infrastructure reachable by other tenants/services, or a writable SQLite cache file). An attacker must be able to write attacker-controlled bytes into the cache backend such that the LangGraph process later reads and deserializes them. This typically requires write access to a networked cache (for example a network-accessible Redis instance with weak/no auth or shared cache infrastructure reachable by other tenants/services) or write access to local cache storage (for example a writable SQLite cache file via permissive file permissions or a shared writable volume). Because exploitation requires write access to the cache storage layer, this is a post-compromise / post-access escalation vector. LangGraph Checkpoint 4.0.0 patches the issue."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 6.6,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "HIGH",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502: Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-02-25T16:53:47.176Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-mhr3-j7m5-c7c9",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-mhr3-j7m5-c7c9"
},
{
"name": "https://github.com/langchain-ai/langgraph/pull/6677",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraph/pull/6677"
},
{
"name": "https://github.com/langchain-ai/langgraph/commit/f91d79d0c86932ded6e3b9f195d5a0bbd5aef99c",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraph/commit/f91d79d0c86932ded6e3b9f195d5a0bbd5aef99c"
},
{
"name": "https://github.com/langchain-ai/langgraph/releases/tag/checkpoint%3D%3D4.0.0",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraph/releases/tag/checkpoint%3D%3D4.0.0"
}
],
"source": {
"advisory": "GHSA-mhr3-j7m5-c7c9",
"discovery": "UNKNOWN"
},
"title": "LangGraph: BaseCache Deserialization of Untrusted Data may lead to Remote Code Execution"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-27794",
"datePublished": "2026-02-25T16:53:47.176Z",
"dateReserved": "2026-02-24T02:31:33.265Z",
"dateUpdated": "2026-02-25T21:00:24.430Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-27022 (GCVE-0-2026-27022)
Vulnerability from cvelistv5 – Published: 2026-02-20 21:06 – Updated: 2026-02-24 18:33
VLAI?
Title
RediSearch Query Injection in @langchain/langgraph-checkpoint-redis
Summary
@langchain/langgraph-checkpoint-redis is the Redis checkpoint and store implementation for LangGraph. A query injection vulnerability exists in the @langchain/langgraph-checkpoint-redis package's filter handling. The RedisSaver and ShallowRedisSaver classes construct RediSearch queries by directly interpolating user-provided filter keys and values without proper escaping. RediSearch has special syntax characters that can modify query behavior, and when user-controlled data contains these characters, the query logic can be manipulated to bypass intended access controls. This vulnerability is fixed in 1.0.2.
Severity ?
6.5 (Medium)
CWE
- CWE-74 - Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')
Assigner
References
| URL | Tags | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langgraphjs |
Affected:
< 1.0.2
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-27022",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-02-24T18:33:08.517946Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-02-24T18:33:25.127Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langgraphjs",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 1.0.2"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "@langchain/langgraph-checkpoint-redis is the Redis checkpoint and store implementation for LangGraph. A query injection vulnerability exists in the @langchain/langgraph-checkpoint-redis package\u0027s filter handling. The RedisSaver and ShallowRedisSaver classes construct RediSearch queries by directly interpolating user-provided filter keys and values without proper escaping. RediSearch has special syntax characters that can modify query behavior, and when user-controlled data contains these characters, the query logic can be manipulated to bypass intended access controls. This vulnerability is fixed in 1.0.2."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-74",
"description": "CWE-74: Improper Neutralization of Special Elements in Output Used by a Downstream Component (\u0027Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-02-20T21:06:53.773Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-5mx2-w598-339m",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-5mx2-w598-339m"
},
{
"name": "https://github.com/langchain-ai/langgraphjs/pull/1943",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraphjs/pull/1943"
},
{
"name": "https://github.com/langchain-ai/langgraphjs/commit/814c76dc3938d0f6f7e17ca3bc11d6a12270b2a1",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraphjs/commit/814c76dc3938d0f6f7e17ca3bc11d6a12270b2a1"
},
{
"name": "https://github.com/langchain-ai/langgraphjs/releases/tag/@langchain/langgraph-checkpoint-redis@1.0.2",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraphjs/releases/tag/@langchain/langgraph-checkpoint-redis@1.0.2"
}
],
"source": {
"advisory": "GHSA-5mx2-w598-339m",
"discovery": "UNKNOWN"
},
"title": "RediSearch Query Injection in @langchain/langgraph-checkpoint-redis"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-27022",
"datePublished": "2026-02-20T21:06:53.773Z",
"dateReserved": "2026-02-17T03:08:23.490Z",
"dateUpdated": "2026-02-24T18:33:25.127Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-26019 (GCVE-0-2026-26019)
Vulnerability from cvelistv5 – Published: 2026-02-11 21:11 – Updated: 2026-02-12 21:14
VLAI?
Title
@langchain/community affected by SSRF Bypass in RecursiveUrlLoader via insufficient URL origin validation
Summary
LangChain is a framework for building LLM-powered applications. Prior to 1.1.14, the RecursiveUrlLoader class in @langchain/community is a web crawler that recursively follows links from a starting URL. Its preventOutside option (enabled by default) is intended to restrict crawling to the same site as the base URL. The implementation used String.startsWith() to compare URLs, which does not perform semantic URL validation. An attacker who controls content on a crawled page could include links to domains that share a string prefix with the target, causing the crawler to follow links to attacker-controlled or internal infrastructure. Additionally, the crawler performed no validation against private or reserved IP addresses. A crawled page could include links targeting cloud metadata services, localhost, or RFC 1918 addresses, and the crawler would fetch them without restriction. This vulnerability is fixed in 1.1.14.
Severity ?
4.1 (Medium)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
| URL | Tags | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchainjs |
Affected:
< 1.1.14
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-26019",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-02-12T21:14:35.104263Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-02-12T21:14:41.756Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchainjs",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 1.1.14"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain is a framework for building LLM-powered applications. Prior to 1.1.14, the RecursiveUrlLoader class in @langchain/community is a web crawler that recursively follows links from a starting URL. Its preventOutside option (enabled by default) is intended to restrict crawling to the same site as the base URL. The implementation used String.startsWith() to compare URLs, which does not perform semantic URL validation. An attacker who controls content on a crawled page could include links to domains that share a string prefix with the target, causing the crawler to follow links to attacker-controlled or internal infrastructure. Additionally, the crawler performed no validation against private or reserved IP addresses. A crawled page could include links targeting cloud metadata services, localhost, or RFC 1918 addresses, and the crawler would fetch them without restriction. This vulnerability is fixed in 1.1.14."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 4.1,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:L/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-02-11T21:11:10.166Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-gf3v-fwqg-4vh7",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-gf3v-fwqg-4vh7"
},
{
"name": "https://github.com/langchain-ai/langchainjs/pull/9990",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/pull/9990"
},
{
"name": "https://github.com/langchain-ai/langchainjs/commit/d5e3db0d01ab321ec70a875805b2f74aefdadf9d",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/commit/d5e3db0d01ab321ec70a875805b2f74aefdadf9d"
},
{
"name": "https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcommunity%401.1.14",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcommunity%401.1.14"
}
],
"source": {
"advisory": "GHSA-gf3v-fwqg-4vh7",
"discovery": "UNKNOWN"
},
"title": "@langchain/community affected by SSRF Bypass in RecursiveUrlLoader via insufficient URL origin validation"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-26019",
"datePublished": "2026-02-11T21:11:10.166Z",
"dateReserved": "2026-02-09T21:36:29.554Z",
"dateUpdated": "2026-02-12T21:14:41.756Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-26013 (GCVE-0-2026-26013)
Vulnerability from cvelistv5 – Published: 2026-02-10 21:51 – Updated: 2026-02-11 21:26
VLAI?
Title
LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages
Summary
LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input. This vulnerability is fixed in 1.2.11.
Severity ?
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
| URL | Tags | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
|||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain |
Affected:
< 1.2.11
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-26013",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-02-11T21:26:20.888102Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-02-11T21:26:34.029Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 1.2.11"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input. This vulnerability is fixed in 1.2.11."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 3.7,
"baseSeverity": "LOW",
"confidentialityImpact": "NONE",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-02-10T21:51:07.741Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r"
},
{
"name": "https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565"
},
{
"name": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11"
}
],
"source": {
"advisory": "GHSA-2g6r-c272-w58r",
"discovery": "UNKNOWN"
},
"title": "LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-26013",
"datePublished": "2026-02-10T21:51:07.741Z",
"dateReserved": "2026-02-09T21:36:29.554Z",
"dateUpdated": "2026-02-11T21:26:34.029Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-25528 (GCVE-0-2026-25528)
Vulnerability from cvelistv5 – Published: 2026-02-09 20:08 – Updated: 2026-02-10 15:59
VLAI?
Title
LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection
Summary
LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. The LangSmith SDK's distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary api_url values through the baggage header, causing the SDK to exfiltrate sensitive trace data to attacker-controlled endpoints. When using distributed tracing, the SDK parses incoming HTTP headers via RunTree.from_headers() in Python or RunTree.fromHeaders() in Typescript. The baggage header can contain replica configurations including api_url and api_key fields. Prior to the fix, these attacker-controlled values were accepted without validation. When a traced operation completes, the SDK's post() and patch() methods send run data to all configured replica URLs, including any injected by an attacker. This vulnerability is fixed in version 0.6.3 of the Python SDK and 0.4.6 of the JavaScript SDK.
Severity ?
5.8 (Medium)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
| URL | Tags | ||||
|---|---|---|---|---|---|
|
|||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langsmith-sdk |
Affected:
>= 0.4.10, <0.6.3
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-25528",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-02-10T15:39:48.039907Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-02-10T15:59:49.992Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langsmith-sdk",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003e= 0.4.10, \u003c0.6.3"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangSmith Client SDKs provide SDK\u0027s for interacting with the LangSmith platform. The LangSmith SDK\u0027s distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary api_url values through the baggage header, causing the SDK to exfiltrate sensitive trace data to attacker-controlled endpoints. When using distributed tracing, the SDK parses incoming HTTP headers via RunTree.from_headers() in Python or RunTree.fromHeaders() in Typescript. The baggage header can contain replica configurations including api_url and api_key fields. Prior to the fix, these attacker-controlled values were accepted without validation. When a traced operation completes, the SDK\u0027s post() and patch() methods send run data to all configured replica URLs, including any injected by an attacker. This vulnerability is fixed in version 0.6.3 of the Python SDK and 0.4.6 of the JavaScript SDK."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 5.8,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-02-09T20:08:32.903Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-v34v-rq6j-cj6p",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-v34v-rq6j-cj6p"
}
],
"source": {
"advisory": "GHSA-v34v-rq6j-cj6p",
"discovery": "UNKNOWN"
},
"title": "LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-25528",
"datePublished": "2026-02-09T20:08:32.903Z",
"dateReserved": "2026-02-02T19:59:47.373Z",
"dateUpdated": "2026-02-10T15:59:49.992Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-68665 (GCVE-0-2025-68665)
Vulnerability from cvelistv5 – Published: 2025-12-23 22:56 – Updated: 2025-12-24 14:38
VLAI?
Title
LangChain serialization injection vulnerability enables secret extraction
Summary
LangChain is a framework for building LLM-powered applications. Prior to @langchain/core versions 0.3.80 and 1.1.8, and prior to langchain versions 0.3.37 and 1.2.3, a serialization injection vulnerability exists in LangChain JS's toJSON() method (and subsequently when string-ifying objects using JSON.stringify(). The method did not escape objects with 'lc' keys when serializing free-form data in kwargs. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data. This issue has been patched in @langchain/core versions 0.3.80 and 1.1.8, and langchain versions 0.3.37 and 1.2.3
Severity ?
8.6 (High)
CWE
- CWE-502 - Deserialization of Untrusted Data
Assigner
References
| URL | Tags | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchainjs |
Affected:
@langchain/core >= 1.0.0, < 1.1.8
Affected: @langchain/core < 0.3.80 Affected: langchain >= 1.0.0, < 1.2.3 Affected: langchain < 0.3.37 |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-68665",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-12-24T14:38:36.252592Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-12-24T14:38:40.268Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-r399-636x-v7f6"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchainjs",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "@langchain/core \u003e= 1.0.0, \u003c 1.1.8"
},
{
"status": "affected",
"version": "@langchain/core \u003c 0.3.80"
},
{
"status": "affected",
"version": "langchain \u003e= 1.0.0, \u003c 1.2.3"
},
{
"status": "affected",
"version": "langchain \u003c 0.3.37"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain is a framework for building LLM-powered applications. Prior to @langchain/core versions 0.3.80 and 1.1.8, and prior to langchain versions 0.3.37 and 1.2.3, a serialization injection vulnerability exists in LangChain JS\u0027s toJSON() method (and subsequently when string-ifying objects using JSON.stringify(). The method did not escape objects with \u0027lc\u0027 keys when serializing free-form data in kwargs. The \u0027lc\u0027 key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data. This issue has been patched in @langchain/core versions 0.3.80 and 1.1.8, and langchain versions 0.3.37 and 1.2.3"
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502: Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-12-23T22:56:04.837Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-r399-636x-v7f6",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langchainjs/security/advisories/GHSA-r399-636x-v7f6"
},
{
"name": "https://github.com/langchain-ai/langchainjs/commit/e5063f9c6e9989ea067dfdff39262b9e7b6aba62",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/commit/e5063f9c6e9989ea067dfdff39262b9e7b6aba62"
},
{
"name": "https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcore%401.1.8",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcore%401.1.8"
},
{
"name": "https://github.com/langchain-ai/langchainjs/releases/tag/langchain%401.2.3",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchainjs/releases/tag/langchain%401.2.3"
}
],
"source": {
"advisory": "GHSA-r399-636x-v7f6",
"discovery": "UNKNOWN"
},
"title": "LangChain serialization injection vulnerability enables secret extraction"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-68665",
"datePublished": "2025-12-23T22:56:04.837Z",
"dateReserved": "2025-12-22T23:28:02.917Z",
"dateUpdated": "2025-12-24T14:38:40.268Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-68664 (GCVE-0-2025-68664)
Vulnerability from cvelistv5 – Published: 2025-12-23 22:47 – Updated: 2025-12-24 14:40
VLAI?
Title
LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
Summary
LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data. This issue has been patched in versions 0.3.81 and 1.2.5.
Severity ?
9.3 (Critical)
CWE
- CWE-502 - Deserialization of Untrusted Data
Assigner
References
| URL | Tags | ||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
|||||||||||||||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain |
Affected:
>= 1.0.0, < 1.2.5
Affected: < 0.3.81 |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-68664",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-12-24T14:40:55.506059Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-12-24T14:40:58.427Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003e= 1.0.0, \u003c 1.2.5"
},
{
"status": "affected",
"version": "\u003c 0.3.81"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain\u0027s dumps() and dumpd() functions. The functions do not escape dictionaries with \u0027lc\u0027 keys when serializing free-form dictionaries. The \u0027lc\u0027 key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data. This issue has been patched in versions 0.3.81 and 1.2.5."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502: Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-12-23T22:47:44.084Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm"
},
{
"name": "https://github.com/langchain-ai/langchain/pull/34455",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/pull/34455"
},
{
"name": "https://github.com/langchain-ai/langchain/pull/34458",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/pull/34458"
},
{
"name": "https://github.com/langchain-ai/langchain/commit/5ec0fa69de31bbe3d76e4cf9cd65a6accb8466c8",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/commit/5ec0fa69de31bbe3d76e4cf9cd65a6accb8466c8"
},
{
"name": "https://github.com/langchain-ai/langchain/commit/d9ec4c5cc78960abd37da79b0250f5642e6f0ce6",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/commit/d9ec4c5cc78960abd37da79b0250f5642e6f0ce6"
},
{
"name": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.81",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.81"
},
{
"name": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.5",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.5"
}
],
"source": {
"advisory": "GHSA-c67j-w6g6-q2cm",
"discovery": "UNKNOWN"
},
"title": "LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-68664",
"datePublished": "2025-12-23T22:47:44.084Z",
"dateReserved": "2025-12-22T23:28:02.917Z",
"dateUpdated": "2025-12-24T14:40:58.427Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-67644 (GCVE-0-2025-67644)
Vulnerability from cvelistv5 – Published: 2025-12-10 23:37 – Updated: 2025-12-11 15:35
VLAI?
Title
LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list method
Summary
LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Versions 3.0.0 and below are vulnerable to SQL injection through the checkpoint implementation. Checkpoint allows attackers to manipulate SQL queries through metadata filter keys, affecting applications that accept untrusted metadata filter keys (not just filter values) in checkpoint search operations. The _metadata_predicate() function constructs SQL queries by interpolating filter keys directly into f-strings without validation. This issue is fixed in version 3.0.1.
Severity ?
7.3 (High)
CWE
- CWE-89 - Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection')
Assigner
References
| URL | Tags | |||||||
|---|---|---|---|---|---|---|---|---|
|
||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langgraph |
Affected:
< 3.0.1
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-67644",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-12-11T15:35:51.799973Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-12-11T15:35:59.816Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langgraph",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 3.0.1"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Versions 3.0.0 and below are vulnerable to SQL injection through the checkpoint implementation. Checkpoint allows attackers to manipulate SQL queries through metadata filter keys, affecting applications that accept untrusted metadata filter keys (not just filter values) in checkpoint search operations. The _metadata_predicate() function constructs SQL queries by interpolating filter keys directly into f-strings without validation. This issue is fixed in version 3.0.1."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "NONE",
"baseScore": 7.3,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-89",
"description": "CWE-89: Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-12-10T23:37:36.182Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-9rwj-6rc7-p77c",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-9rwj-6rc7-p77c"
},
{
"name": "https://github.com/langchain-ai/langgraph/commit/297242913f8ad2143ee3e2f72e67db0911d48e2a",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraph/commit/297242913f8ad2143ee3e2f72e67db0911d48e2a"
}
],
"source": {
"advisory": "GHSA-9rwj-6rc7-p77c",
"discovery": "UNKNOWN"
},
"title": "LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list method"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-67644",
"datePublished": "2025-12-10T23:37:36.182Z",
"dateReserved": "2025-12-09T18:36:41.330Z",
"dateUpdated": "2025-12-11T15:35:59.816Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-65106 (GCVE-0-2025-65106)
Vulnerability from cvelistv5 – Published: 2025-11-21 21:43 – Updated: 2025-11-21 21:53
VLAI?
Title
LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates
Summary
LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings (not just template variables) in ChatPromptTemplate and related prompt template classes. This issue has been patched in versions 0.3.80 and 1.0.7.
Severity ?
CWE
- CWE-1336 - Improper Neutralization of Special Elements Used in a Template Engine
Assigner
References
| URL | Tags | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
|||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain |
Affected:
>= 1.0.0, < 1.0.7
Affected: < 0.3.80 |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-65106",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-11-21T21:53:02.259742Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-11-21T21:53:19.566Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003e= 1.0.0, \u003c 1.0.7"
},
{
"status": "affected",
"version": "\u003c 0.3.80"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain\u0027s prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings (not just template variables) in ChatPromptTemplate and related prompt template classes. This issue has been patched in versions 0.3.80 and 1.0.7."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"attackVector": "NETWORK",
"baseScore": 8.3,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "LOW"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-1336",
"description": "CWE-1336: Improper Neutralization of Special Elements Used in a Template Engine",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-11-21T21:43:02.461Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-6qv9-48xg-fc7f",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-6qv9-48xg-fc7f"
},
{
"name": "https://github.com/langchain-ai/langchain/commit/c4b6ba254e1a49ed91f2e268e6484011c540542a",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/commit/c4b6ba254e1a49ed91f2e268e6484011c540542a"
},
{
"name": "https://github.com/langchain-ai/langchain/commit/fa7789d6c21222b85211755d822ef698d3b34e00",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langchain/commit/fa7789d6c21222b85211755d822ef698d3b34e00"
}
],
"source": {
"advisory": "GHSA-6qv9-48xg-fc7f",
"discovery": "UNKNOWN"
},
"title": "LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-65106",
"datePublished": "2025-11-21T21:43:02.461Z",
"dateReserved": "2025-11-17T20:55:34.694Z",
"dateUpdated": "2025-11-21T21:53:19.566Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-64439 (GCVE-0-2025-64439)
Vulnerability from cvelistv5 – Published: 2025-11-07 20:15 – Updated: 2025-11-07 20:21
VLAI?
Title
LangGraph Checkpoint affected by RCE in "json" mode of JsonPlusSerializer
Summary
LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 2.1.2 and below, the JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a Remote Code Execution (RCE) vulnerability when deserializing payloads saved in the "json" serialization mode. By default, the serializer attempts to use "msgpack" for serialization. However, prior to version 3.0 of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail, it would fall back to using the "json" mode. This issue is fixed in version 3.0.0.
Severity ?
CWE
- CWE-502 - Deserialization of Untrusted Data
Assigner
References
| URL | Tags | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||||||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langgraph |
Affected:
< 3.0.0
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-64439",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-11-07T20:21:40.598293Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-11-07T20:21:52.610Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langgraph",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 3.0.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 2.1.2 and below, the JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a Remote Code Execution (RCE) vulnerability when deserializing payloads saved in the \"json\" serialization mode. By default, the serializer attempts to use \"msgpack\" for serialization. However, prior to version 3.0 of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail, it would fall back to using the \"json\" mode. This issue is fixed in version 3.0.0."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"attackVector": "NETWORK",
"baseScore": 7.4,
"baseSeverity": "HIGH",
"privilegesRequired": "LOW",
"subAvailabilityImpact": "HIGH",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "HIGH",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:H",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "HIGH"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502: Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-11-07T20:15:21.710Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-wwqv-p2pp-99h5",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-wwqv-p2pp-99h5"
},
{
"name": "https://github.com/langchain-ai/langgraph/commit/c5744f583b11745cd406f3059903e17bbcdcc8ac",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraph/commit/c5744f583b11745cd406f3059903e17bbcdcc8ac"
},
{
"name": "https://github.com/langchain-ai/langgraph/blob/c5744f583b11745cd406f3059903e17bbcdcc8ac/libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraph/blob/c5744f583b11745cd406f3059903e17bbcdcc8ac/libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py"
},
{
"name": "https://github.com/langchain-ai/langgraph/releases/tag/checkpoint%3D%3D3.0.0",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraph/releases/tag/checkpoint%3D%3D3.0.0"
}
],
"source": {
"advisory": "GHSA-wwqv-p2pp-99h5",
"discovery": "UNKNOWN"
},
"title": "LangGraph Checkpoint affected by RCE in \"json\" mode of JsonPlusSerializer"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-64439",
"datePublished": "2025-11-07T20:15:21.710Z",
"dateReserved": "2025-11-03T22:12:51.366Z",
"dateUpdated": "2025-11-07T20:21:52.610Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-64104 (GCVE-0-2025-64104)
Vulnerability from cvelistv5 – Published: 2025-10-29 18:55 – Updated: 2025-10-30 15:33
VLAI?
Title
LangGraph SQLite Checkpoint Filter Key SQL Injection POC for SqliteStore
Summary
LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Prior to 2.0.11, LangGraph's SQLite store implementation contains SQL injection vulnerabilities using direct string concatenation without proper parameterization, allowing attackers to inject arbitrary SQL and bypass access controls. This vulnerability is fixed in 2.0.11.
Severity ?
7.3 (High)
CWE
- CWE-89 - Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection')
Assigner
References
| URL | Tags | |||||||
|---|---|---|---|---|---|---|---|---|
|
||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langgraph |
Affected:
< 2.0.11
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-64104",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-10-30T15:33:02.801013Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-10-30T15:33:07.541Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-7p73-8jqx-23r8"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langgraph",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 2.0.11"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Prior to 2.0.11, LangGraph\u0027s SQLite store implementation contains SQL injection vulnerabilities using direct string concatenation without proper parameterization, allowing attackers to inject arbitrary SQL and bypass access controls. This vulnerability is fixed in 2.0.11."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "NONE",
"baseScore": 7.3,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-89",
"description": "CWE-89: Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-10-29T18:55:06.129Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-7p73-8jqx-23r8",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-7p73-8jqx-23r8"
},
{
"name": "https://github.com/langchain-ai/langgraph/commit/bc9d45b476101e441cb1cc602dea03eb29232de4",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/langgraph/commit/bc9d45b476101e441cb1cc602dea03eb29232de4"
}
],
"source": {
"advisory": "GHSA-7p73-8jqx-23r8",
"discovery": "UNKNOWN"
},
"title": "LangGraph SQLite Checkpoint Filter Key SQL Injection POC for SqliteStore"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-64104",
"datePublished": "2025-10-29T18:55:06.129Z",
"dateReserved": "2025-10-27T15:26:14.127Z",
"dateUpdated": "2025-10-30T15:33:07.541Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-8709 (GCVE-0-2025-8709)
Vulnerability from cvelistv5 – Published: 2025-10-26 05:38 – Updated: 2025-10-28 14:32
VLAI?
Title
SQL Injection in langchain-ai/langchain
Summary
A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators ($eq, $ne, $gt, $lt, $gte, $lte) where direct string concatenation is used without proper parameterization. This allows attackers to inject arbitrary SQL, leading to unauthorized access to all documents, data exfiltration of sensitive fields such as passwords and API keys, and a complete bypass of application-level security filters.
Severity ?
7.3 (High)
CWE
- CWE-89 - Improper Neutralization of Special Elements used in an SQL Command
Assigner
References
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-ai/langchain |
Affected:
unspecified , ≤ latest
(custom)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-8709",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-10-28T14:32:35.114025Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-10-28T14:32:39.540Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://huntr.com/bounties/9793f4b3-76f8-44a4-989f-49a2177ee118"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain-ai/langchain",
"vendor": "langchain-ai",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph\u0027s SQLite store implementation. The affected version is langgraph-checkpoint-sqlite 2.0.10. The vulnerability arises from improper handling of filter operators ($eq, $ne, $gt, $lt, $gte, $lte) where direct string concatenation is used without proper parameterization. This allows attackers to inject arbitrary SQL, leading to unauthorized access to all documents, data exfiltration of sensitive fields such as passwords and API keys, and a complete bypass of application-level security filters."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "NONE",
"baseScore": 7.3,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-89",
"description": "CWE-89 Improper Neutralization of Special Elements used in an SQL Command",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-10-26T05:38:55.335Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/9793f4b3-76f8-44a4-989f-49a2177ee118"
}
],
"source": {
"advisory": "9793f4b3-76f8-44a4-989f-49a2177ee118",
"discovery": "EXTERNAL"
},
"title": "SQL Injection in langchain-ai/langchain"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2025-8709",
"datePublished": "2025-10-26T05:38:55.335Z",
"dateReserved": "2025-08-07T14:55:22.718Z",
"dateUpdated": "2025-10-28T14:32:39.540Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2025-6985 (GCVE-0-2025-6985)
Vulnerability from cvelistv5 – Published: 2025-10-06 17:58 – Updated: 2025-10-06 18:10
VLAI?
Title
XXE Vulnerability in langchain-ai/langchain
Summary
The HTMLSectionSplitter class in langchain-text-splitters version 0.3.8 is vulnerable to XML External Entity (XXE) attacks due to unsafe XSLT parsing. This vulnerability arises because the class allows the use of arbitrary XSLT stylesheets, which are parsed using lxml.etree.parse() and lxml.etree.XSLT() without any hardening measures. In lxml versions up to 4.9.x, external entities are resolved by default, allowing attackers to read arbitrary local files or perform outbound HTTP(S) fetches. In lxml versions 5.0 and above, while entity expansion is disabled, the XSLT document() function can still read any URI unless XSLTAccessControl is applied. This vulnerability allows remote attackers to gain read-only access to any file the LangChain process can reach, including sensitive files such as SSH keys, environment files, source code, or cloud metadata. No authentication, special privileges, or user interaction are required, and the issue is exploitable in default deployments that enable custom XSLT.
Severity ?
7.5 (High)
CWE
- CWE-611 - Improper Restriction of XML External Entity Reference
Assigner
References
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-ai/langchain |
Affected:
unspecified , ≤ latest
(custom)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-6985",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-10-06T18:10:17.774029Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-10-06T18:10:28.811Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain-ai/langchain",
"vendor": "langchain-ai",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "The HTMLSectionSplitter class in langchain-text-splitters version 0.3.8 is vulnerable to XML External Entity (XXE) attacks due to unsafe XSLT parsing. This vulnerability arises because the class allows the use of arbitrary XSLT stylesheets, which are parsed using lxml.etree.parse() and lxml.etree.XSLT() without any hardening measures. In lxml versions up to 4.9.x, external entities are resolved by default, allowing attackers to read arbitrary local files or perform outbound HTTP(S) fetches. In lxml versions 5.0 and above, while entity expansion is disabled, the XSLT document() function can still read any URI unless XSLTAccessControl is applied. This vulnerability allows remote attackers to gain read-only access to any file the LangChain process can reach, including sensitive files such as SSH keys, environment files, source code, or cloud metadata. No authentication, special privileges, or user interaction are required, and the issue is exploitable in default deployments that enable custom XSLT."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-611",
"description": "CWE-611 Improper Restriction of XML External Entity Reference",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-10-06T17:58:29.078Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/cf78abbb-df3b-43de-b6ee-132b73ff8331"
}
],
"source": {
"advisory": "cf78abbb-df3b-43de-b6ee-132b73ff8331",
"discovery": "EXTERNAL"
},
"title": "XXE Vulnerability in langchain-ai/langchain"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2025-6985",
"datePublished": "2025-10-06T17:58:29.078Z",
"dateReserved": "2025-07-01T20:33:58.220Z",
"dateUpdated": "2025-10-06T18:10:28.811Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2025-6984 (GCVE-0-2025-6984)
Vulnerability from cvelistv5 – Published: 2025-09-04 08:07 – Updated: 2025-09-04 20:07
VLAI?
Title
Sensitive Information Disclosure Due to Insecure XML Parsing in langchain-ai/langchain
Summary
The langchain-ai/langchain project, specifically the EverNoteLoader component, is vulnerable to XML External Entity (XXE) attacks due to insecure XML parsing. The affected version is 0.3.63. The vulnerability arises from the use of etree.iterparse() without disabling external entity references, which can lead to sensitive information disclosure. An attacker could exploit this by crafting a malicious XML payload that references local files, potentially exposing sensitive data such as /etc/passwd.
Severity ?
7.5 (High)
CWE
- CWE-200 - Exposure of Sensitive Information to an Unauthorized Actor
Assigner
References
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-ai/langchain |
Affected:
unspecified , ≤ latest
(custom)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-6984",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-09-04T20:07:23.933476Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-09-04T20:07:31.531Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain-ai/langchain",
"vendor": "langchain-ai",
"versions": [
{
"lessThanOrEqual": "latest",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "The langchain-ai/langchain project, specifically the EverNoteLoader component, is vulnerable to XML External Entity (XXE) attacks due to insecure XML parsing. The affected version is 0.3.63. The vulnerability arises from the use of etree.iterparse() without disabling external entity references, which can lead to sensitive information disclosure. An attacker could exploit this by crafting a malicious XML payload that references local files, potentially exposing sensitive data such as /etc/passwd."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-200",
"description": "CWE-200 Exposure of Sensitive Information to an Unauthorized Actor",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-09-04T08:07:41.996Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/a6b521cf-258c-41c0-9edb-d8ef976abb2a"
}
],
"source": {
"advisory": "a6b521cf-258c-41c0-9edb-d8ef976abb2a",
"discovery": "EXTERNAL"
},
"title": "Sensitive Information Disclosure Due to Insecure XML Parsing in langchain-ai/langchain"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2025-6984",
"datePublished": "2025-09-04T08:07:41.996Z",
"dateReserved": "2025-07-01T20:19:39.922Z",
"dateUpdated": "2025-09-04T20:07:31.531Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2025-2828 (GCVE-0-2025-2828)
Vulnerability from cvelistv5 – Published: 2025-06-23 20:42 – Updated: 2025-06-24 13:32
VLAI?
Title
SSRF Vulnerability in RequestsToolkit in langchain-ai/langchain
Summary
A Server-Side Request Forgery (SSRF) vulnerability exists in the RequestsToolkit component of the langchain-community package (specifically, langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit) in langchain-ai/langchain version 0.0.27. This vulnerability occurs because the toolkit does not enforce restrictions on requests to remote internet addresses, allowing it to also access local addresses. As a result, an attacker could exploit this flaw to perform port scans, access local services, retrieve instance metadata from cloud environments (e.g., Azure, AWS), and interact with servers on the local network. This issue has been fixed in version 0.0.28.
Severity ?
8.4 (High)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-ai/langchain |
Affected:
unspecified , < 0.0.28
(custom)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-2828",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-06-24T13:32:17.049400Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-06-24T13:32:19.925Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://huntr.com/bounties/8f771040-7f34-420a-b96b-5b93d4a99afc"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain-ai/langchain",
"vendor": "langchain-ai",
"versions": [
{
"lessThan": "0.0.28",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A Server-Side Request Forgery (SSRF) vulnerability exists in the RequestsToolkit component of the langchain-community package (specifically, langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit) in langchain-ai/langchain version 0.0.27. This vulnerability occurs because the toolkit does not enforce restrictions on requests to remote internet addresses, allowing it to also access local addresses. As a result, an attacker could exploit this flaw to perform port scans, access local services, retrieve instance metadata from cloud environments (e.g., Azure, AWS), and interact with servers on the local network. This issue has been fixed in version 0.0.28."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.4,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "HIGH",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:H/UI:R/S:C/C:H/I:H/A:H",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918 Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-06-23T20:42:28.639Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/8f771040-7f34-420a-b96b-5b93d4a99afc"
},
{
"url": "https://github.com/langchain-ai/langchain/commit/e188d4ecb085d4561a0be3c583d26aa9c2c3283f"
}
],
"source": {
"advisory": "8f771040-7f34-420a-b96b-5b93d4a99afc",
"discovery": "EXTERNAL"
},
"title": "SSRF Vulnerability in RequestsToolkit in langchain-ai/langchain"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2025-2828",
"datePublished": "2025-06-23T20:42:28.639Z",
"dateReserved": "2025-03-26T17:46:45.448Z",
"dateUpdated": "2025-06-24T13:32:19.925Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-10940 (GCVE-0-2024-10940)
Vulnerability from cvelistv5 – Published: 2025-03-20 10:08 – Updated: 2025-03-20 19:02
VLAI?
Title
Exposure of Sensitive System Information via ImagePromptTemplate in langchain-ai/langchain
Summary
A vulnerability in langchain-core versions >=0.1.17,<0.1.53, >=0.2.0,<0.2.43, and >=0.3.0,<0.3.15 allows unauthorized users to read arbitrary files from the host file system. The issue arises from the ability to create langchain_core.prompts.ImagePromptTemplate's (and by extension langchain_core.prompts.ChatPromptTemplate's) with input variables that can read any user-specified path from the server file system. If the outputs of these prompt templates are exposed to the user, either directly or through downstream model outputs, it can lead to the exposure of sensitive information.
Severity ?
5.3 (Medium)
CWE
- CWE-497 - Exposure of Sensitive System Information to an Unauthorized Control Sphere
Assigner
References
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-ai/langchain |
Affected:
unspecified , < 0.3.15
(custom)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-10940",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-03-20T17:54:57.246319Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-03-20T19:02:58.871Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain-ai/langchain",
"vendor": "langchain-ai",
"versions": [
{
"lessThan": "0.3.15",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A vulnerability in langchain-core versions \u003e=0.1.17,\u003c0.1.53, \u003e=0.2.0,\u003c0.2.43, and \u003e=0.3.0,\u003c0.3.15 allows unauthorized users to read arbitrary files from the host file system. The issue arises from the ability to create langchain_core.prompts.ImagePromptTemplate\u0027s (and by extension langchain_core.prompts.ChatPromptTemplate\u0027s) with input variables that can read any user-specified path from the server file system. If the outputs of these prompt templates are exposed to the user, either directly or through downstream model outputs, it can lead to the exposure of sensitive information."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 5.3,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-497",
"description": "CWE-497 Exposure of Sensitive System Information to an Unauthorized Control Sphere",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-03-20T10:08:48.628Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/be1ee1cb-2147-4ff4-a57b-b6045271cf27"
},
{
"url": "https://github.com/langchain-ai/langchain/commit/c1e742347f9701aadba8920e4d1f79a636e50b68"
}
],
"source": {
"advisory": "be1ee1cb-2147-4ff4-a57b-b6045271cf27",
"discovery": "EXTERNAL"
},
"title": "Exposure of Sensitive System Information via ImagePromptTemplate in langchain-ai/langchain"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-10940",
"datePublished": "2025-03-20T10:08:48.628Z",
"dateReserved": "2024-11-06T19:50:09.607Z",
"dateUpdated": "2025-03-20T19:02:58.871Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-8309 (GCVE-0-2024-8309)
Vulnerability from cvelistv5 – Published: 2024-10-29 12:50 – Updated: 2025-10-15 12:50
VLAI?
Title
SQL Injection in langchain-ai/langchain
Summary
A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial of service (DoS) by deleting all data, breaches in multi-tenant security environments, and data integrity issues. Attackers can create, update, or delete nodes and relationships without proper authorization, extract sensitive data, disrupt services, access data across different tenants, and compromise the integrity of the database.
Severity ?
4.9 (Medium)
CWE
- CWE-89 - Improper Neutralization of Special Elements used in an SQL Command
Assigner
References
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-ai/langchain |
Affected:
unspecified , < 0.3.0
(custom)
|
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain-ai:langchain:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "langchain",
"vendor": "langchain-ai",
"versions": [
{
"lessThan": "0.3.0",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-8309",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-10-29T13:50:16.254824Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-10-29T18:14:46.661Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain-ai/langchain",
"vendor": "langchain-ai",
"versions": [
{
"lessThan": "0.3.0",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial of service (DoS) by deleting all data, breaches in multi-tenant security environments, and data integrity issues. Attackers can create, update, or delete nodes and relationships without proper authorization, extract sensitive data, disrupt services, access data across different tenants, and compromise the integrity of the database."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "HIGH",
"attackVector": "LOCAL",
"availabilityImpact": "LOW",
"baseScore": 4.9,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.0/AV:L/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-89",
"description": "CWE-89 Improper Neutralization of Special Elements used in an SQL Command",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-10-15T12:50:40.456Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/8f4ad910-7fdc-4089-8f0a-b5df5f32e7c5"
},
{
"url": "https://github.com/langchain-ai/langchain/commit/c2a3021bb0c5f54649d380b42a0684ca5778c255"
}
],
"source": {
"advisory": "8f4ad910-7fdc-4089-8f0a-b5df5f32e7c5",
"discovery": "EXTERNAL"
},
"title": "SQL Injection in langchain-ai/langchain"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-8309",
"datePublished": "2024-10-29T12:50:13.198Z",
"dateReserved": "2024-08-29T13:51:04.837Z",
"dateUpdated": "2025-10-15T12:50:40.456Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-7042 (GCVE-0-2024-7042)
Vulnerability from cvelistv5 – Published: 2024-10-29 12:50 – Updated: 2025-10-15 12:50
VLAI?
Title
Prompt Injection in langchain-ai/langchainjs Leading to SQL Injection
Summary
A vulnerability in the GraphCypherQAChain class of langchain-ai/langchainjs versions 0.2.5 and all versions with this class allows for prompt injection, leading to SQL injection. This vulnerability permits unauthorized data manipulation, data exfiltration, denial of service (DoS) by deleting all data, breaches in multi-tenant security environments, and data integrity issues. Attackers can create, update, or delete nodes and relationships without proper authorization, extract sensitive data, disrupt services, access data across different tenants, and compromise the integrity of the database.
Severity ?
4.9 (Medium)
CWE
- CWE-89 - Improper Neutralization of Special Elements used in an SQL Command
Assigner
References
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-ai/langchainjs |
Affected:
unspecified , < 0.3.1
(custom)
|
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain-ai:langchainjs:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "langchainjs",
"vendor": "langchain-ai",
"versions": [
{
"lessThan": "0.3.1",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-7042",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-10-29T13:50:49.711929Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-10-29T18:13:22.249Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain-ai/langchainjs",
"vendor": "langchain-ai",
"versions": [
{
"lessThan": "0.3.1",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A vulnerability in the GraphCypherQAChain class of langchain-ai/langchainjs versions 0.2.5 and all versions with this class allows for prompt injection, leading to SQL injection. This vulnerability permits unauthorized data manipulation, data exfiltration, denial of service (DoS) by deleting all data, breaches in multi-tenant security environments, and data integrity issues. Attackers can create, update, or delete nodes and relationships without proper authorization, extract sensitive data, disrupt services, access data across different tenants, and compromise the integrity of the database."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "HIGH",
"attackVector": "LOCAL",
"availabilityImpact": "LOW",
"baseScore": 4.9,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.0/AV:L/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:L",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-89",
"description": "CWE-89 Improper Neutralization of Special Elements used in an SQL Command",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-10-15T12:50:36.199Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/b612defb-1104-4fff-9fef-001ab07c7b2d"
},
{
"url": "https://github.com/langchain-ai/langchainjs/commit/615b9d9ab30a2d23a2f95fb8d7acfdf4b41ad7a6"
}
],
"source": {
"advisory": "b612defb-1104-4fff-9fef-001ab07c7b2d",
"discovery": "EXTERNAL"
},
"title": "Prompt Injection in langchain-ai/langchainjs Leading to SQL Injection"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-7042",
"datePublished": "2024-10-29T12:50:05.375Z",
"dateReserved": "2024-07-23T18:41:58.788Z",
"dateUpdated": "2025-10-15T12:50:36.199Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-7774 (GCVE-0-2024-7774)
Vulnerability from cvelistv5 – Published: 2024-10-29 12:49 – Updated: 2024-10-29 13:31
VLAI?
Title
Path Traversal in langchain-ai/langchainjs
Summary
A path traversal vulnerability exists in the `getFullPath` method of langchain-ai/langchainjs version 0.2.5. This vulnerability allows attackers to save files anywhere in the filesystem, overwrite existing text files, read `.txt` files, and delete files. The vulnerability is exploited through the `setFileContent`, `getParsedFile`, and `mdelete` methods, which do not properly sanitize user input.
Severity ?
6.5 (Medium)
CWE
- CWE-29 - Path Traversal: '\..\filename'
Assigner
References
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-ai/langchainjs |
Affected:
unspecified , < 0.2.19
(custom)
|
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain-ai:langchain-ai\\/langchainjs:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "langchain-ai\\/langchainjs",
"vendor": "langchain-ai",
"versions": [
{
"lessThan": "0.2.19",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-7774",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-10-29T13:28:45.771600Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-10-29T13:31:38.566Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain-ai/langchainjs",
"vendor": "langchain-ai",
"versions": [
{
"lessThan": "0.2.19",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A path traversal vulnerability exists in the `getFullPath` method of langchain-ai/langchainjs version 0.2.5. This vulnerability allows attackers to save files anywhere in the filesystem, overwrite existing text files, read `.txt` files, and delete files. The vulnerability is exploited through the `setFileContent`, `getParsedFile`, and `mdelete` methods, which do not properly sanitize user input."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "LOW",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-29",
"description": "CWE-29 Path Traversal: \u0027\\..\\filename\u0027",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-10-29T12:49:21.165Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/8fe40685-b714-4191-af7a-3de5e5628cee"
},
{
"url": "https://github.com/langchain-ai/langchainjs/commit/a0fad77d6b569e5872bd4a9d33be0c0785e538a9"
}
],
"source": {
"advisory": "8fe40685-b714-4191-af7a-3de5e5628cee",
"discovery": "EXTERNAL"
},
"title": "Path Traversal in langchain-ai/langchainjs"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-7774",
"datePublished": "2024-10-29T12:49:21.165Z",
"dateReserved": "2024-08-13T21:13:38.960Z",
"dateUpdated": "2024-10-29T13:31:38.566Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-5998 (GCVE-0-2024-5998)
Vulnerability from cvelistv5 – Published: 2024-09-17 11:50 – Updated: 2024-09-17 13:34
VLAI?
Title
Deserialization of Untrusted Data in langchain-ai/langchain
Summary
A vulnerability in the FAISS.deserialize_from_bytes function of langchain-ai/langchain allows for pickle deserialization of untrusted data. This can lead to the execution of arbitrary commands via the os.system function. The issue affects the latest version of the product.
Severity ?
5.2 (Medium)
CWE
- CWE-502 - Deserialization of Untrusted Data
Assigner
References
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-ai/langchain |
Affected:
unspecified , < 0.2.9
(custom)
|
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "langchain",
"vendor": "langchain",
"versions": [
{
"lessThan": "0.2.9",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-5998",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-09-17T13:28:59.648989Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-09-17T13:34:15.648Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langchain-ai/langchain",
"vendor": "langchain-ai",
"versions": [
{
"lessThan": "0.2.9",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A vulnerability in the FAISS.deserialize_from_bytes function of langchain-ai/langchain allows for pickle deserialization of untrusted data. This can lead to the execution of arbitrary commands via the os.system function. The issue affects the latest version of the product."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "PHYSICAL",
"availabilityImpact": "LOW",
"baseScore": 5.2,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.0/AV:P/AC:L/PR:L/UI:R/S:U/C:H/I:L/A:L",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502 Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-09-17T11:50:13.813Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/fa3a2753-57c3-4e08-a176-d7a3ffda28fe"
},
{
"url": "https://github.com/langchain-ai/langchain/commit/604dfe2d99246b0c09f047c604f0c63eafba31e7"
}
],
"source": {
"advisory": "fa3a2753-57c3-4e08-a176-d7a3ffda28fe",
"discovery": "EXTERNAL"
},
"title": "Deserialization of Untrusted Data in langchain-ai/langchain"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-5998",
"datePublished": "2024-09-17T11:50:13.813Z",
"dateReserved": "2024-06-14T13:32:32.118Z",
"dateUpdated": "2024-09-17T13:34:15.648Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-2965 (GCVE-0-2024-2965)
Vulnerability from cvelistv5 – Published: 2024-06-06 18:52 – Updated: 2025-10-15 12:50
VLAI?
Title
Denial-of-Service in LangChain SitemapLoader in langchain-ai/langchain
Summary
A Denial-of-Service (DoS) vulnerability exists in the `SitemapLoader` class of the `langchain-ai/langchain` repository, affecting all versions. The `parse_sitemap` method, responsible for parsing sitemaps and extracting URLs, lacks a mechanism to prevent infinite recursion when a sitemap URL refers to the current sitemap itself. This oversight allows for the possibility of an infinite loop, leading to a crash by exceeding the maximum recursion depth in Python. This vulnerability can be exploited to occupy server socket/port resources and crash the Python process, impacting the availability of services relying on this functionality.
Severity ?
4.2 (Medium)
CWE
- CWE-674 - Uncontrolled Recursion
Assigner
References
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| langchain-ai | langchain-ai/langchain |
Affected:
unspecified , < 0.2.5
(custom)
|
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "langchain",
"vendor": "langchain",
"versions": [
{
"lessThan": "*",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-2965",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-06-07T13:30:27.318825Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-06-07T19:03:21.881Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
},
{
"providerMetadata": {
"dateUpdated": "2024-08-01T19:32:42.613Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"tags": [
"x_transferred"
],
"url": "https://huntr.com/bounties/90b0776d-9fa6-4841-aac4-09fde5918cae"
}
],
"title": "CVE Program Container"
}
],
"cna": {
"affected": [
{
"product": "langchain-ai/langchain",
"vendor": "langchain-ai",
"versions": [
{
"lessThan": "0.2.5",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "A Denial-of-Service (DoS) vulnerability exists in the `SitemapLoader` class of the `langchain-ai/langchain` repository, affecting all versions. The `parse_sitemap` method, responsible for parsing sitemaps and extracting URLs, lacks a mechanism to prevent infinite recursion when a sitemap URL refers to the current sitemap itself. This oversight allows for the possibility of an infinite loop, leading to a crash by exceeding the maximum recursion depth in Python. This vulnerability can be exploited to occupy server socket/port resources and crash the Python process, impacting the availability of services relying on this functionality."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "HIGH",
"attackVector": "PHYSICAL",
"availabilityImpact": "HIGH",
"baseScore": 4.2,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.0/AV:P/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-674",
"description": "CWE-674 Uncontrolled Recursion",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-10-15T12:50:22.559Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/90b0776d-9fa6-4841-aac4-09fde5918cae"
},
{
"url": "https://github.com/langchain-ai/langchain/commit/73c42306745b0831aa6fe7fe4eeb70d2c2d87a82"
}
],
"source": {
"advisory": "90b0776d-9fa6-4841-aac4-09fde5918cae",
"discovery": "EXTERNAL"
},
"title": "Denial-of-Service in LangChain SitemapLoader in langchain-ai/langchain"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-2965",
"datePublished": "2024-06-06T18:52:54.353Z",
"dateReserved": "2024-03-26T19:55:25.763Z",
"dateUpdated": "2025-10-15T12:50:22.559Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}