Search
Find a vulnerability
Search criteria
8 vulnerabilities found for langchain-experimental by langchain
CVE-2024-46946 (GCVE-0-2024-46946)
Vulnerability from nvd – Published: 2024-09-19 00:00 – Updated: 2024-09-19 14:06
VLAI
EPSS
VEX
Summary
langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 (2023-10-05).
Severity
9.8 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- n/a
- CWE-20 - Improper Input Validation
Assigner
References
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| langchain | langchain_experimental |
Affected:
0.1.17 , ≤ 0.3.0
(custom)
cpe:2.3:a:langchain:langchain_experimental:*:*:*:*:*:python:*:* |
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain:langchain_experimental:*:*:*:*:*:python:*:*"
],
"defaultStatus": "unknown",
"product": "langchain_experimental",
"vendor": "langchain",
"versions": [
{
"lessThanOrEqual": "0.3.0",
"status": "affected",
"version": "0.1.17",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
},
{
"other": {
"content": {
"id": "CVE-2024-46946",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-09-19T14:04:46.354291Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-20",
"description": "CWE-20 Improper Input Validation",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-09-19T14:06:52.692Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "n/a",
"vendor": "n/a",
"versions": [
{
"status": "affected",
"version": "n/a"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 (2023-10-05)."
}
],
"problemTypes": [
{
"descriptions": [
{
"description": "n/a",
"lang": "en",
"type": "text"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-09-19T05:03:25.650Z",
"orgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"shortName": "mitre"
},
"references": [
{
"url": "https://cwe.mitre.org/data/definitions/95.html"
},
{
"url": "https://github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0"
},
{
"url": "https://docs.sympy.org/latest/modules/codegen.html"
},
{
"url": "https://gist.github.com/12end/68c0c58d2564ef4141bccd4651480820#file-cve-2024-46946-txt"
}
]
}
},
"cveMetadata": {
"assignerOrgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"assignerShortName": "mitre",
"cveId": "CVE-2024-46946",
"datePublished": "2024-09-19T00:00:00.000Z",
"dateReserved": "2024-09-15T00:00:00.000Z",
"dateUpdated": "2024-09-19T14:06:52.692Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-21513 (GCVE-0-2024-21513)
Vulnerability from nvd – Published: 2024-07-15 05:00 – Updated: 2024-08-01 22:20
VLAI
EPSS
VEX
Summary
Versions of the package langchain-experimental from 0.0.15 and before 0.0.21 are vulnerable to Arbitrary Code Execution when retrieving values from the database, the code will attempt to call 'eval' on all values. An attacker can exploit this vulnerability and execute arbitrary python code if they can control the input prompt and the server is configured with VectorSQLDatabaseChain.
**Notes:**
Impact on the Confidentiality, Integrity and Availability of the vulnerable component:
Confidentiality: Code execution happens within the impacted component, in this case langchain-experimental, so all resources are necessarily accessible.
Integrity: There is nothing protected by the impacted component inherently. Although anything returned from the component counts as 'information' for which the trustworthiness can be compromised.
Availability: The loss of availability isn't caused by the attack itself, but it happens as a result during the attacker's post-exploitation steps.
Impact on the Confidentiality, Integrity and Availability of the subsequent system:
As a legitimate low-privileged user of the package (PR:L) the attacker does not have more access to data owned by the package as a result of this vulnerability than they did with normal usage (e.g. can query the DB). The unintended action that one can perform by breaking out of the app environment and exfiltrating files, making remote connections etc. happens during the post exploitation phase in the subsequent system - in this case, the OS.
AT:P: An attacker needs to be able to influence the input prompt, whilst the server is configured with the VectorSQLDatabaseChain plugin.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| n/a | langchain-experimental |
Affected:
0.0.15 , < 0.0.21
(semver)
|
|
| langchain | langchain_experimental |
Affected:
0.0.15 , < 0.0.21
(custom)
cpe:2.3:a:langchain:langchain_experimental:0.0.15:*:*:*:*:python:*:* |
Credits
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain:langchain_experimental:0.0.15:*:*:*:*:python:*:*"
],
"defaultStatus": "unknown",
"product": "langchain_experimental",
"vendor": "langchain",
"versions": [
{
"lessThan": "0.0.21",
"status": "affected",
"version": "0.0.15",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-21513",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-07-15T19:05:37.533971Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94 Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-07-15T19:10:56.283Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
},
{
"providerMetadata": {
"dateUpdated": "2024-08-01T22:20:40.879Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"tags": [
"x_transferred"
],
"url": "https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAINEXPERIMENTAL-7278171"
},
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/blob/672907bbbb7c38bf19787b78e4ffd7c8a9026fe4/libs/experimental/langchain_experimental/sql/vector_sql.py%23L81"
},
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/commit/7b13292e3544b2f5f2bfb8a27a062ea2b0c34561"
}
],
"title": "CVE Program Container"
}
],
"cna": {
"affected": [
{
"product": "langchain-experimental",
"vendor": "n/a",
"versions": [
{
"lessThan": "0.0.21",
"status": "affected",
"version": "0.0.15",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"value": "Rory McNamara (Snyk Security Research)"
}
],
"descriptions": [
{
"lang": "en",
"value": "Versions of the package langchain-experimental from 0.0.15 and before 0.0.21 are vulnerable to Arbitrary Code Execution when retrieving values from the database, the code will attempt to call \u0027eval\u0027 on all values. An attacker can exploit this vulnerability and execute arbitrary python code if they can control the input prompt and the server is configured with VectorSQLDatabaseChain.\r\r**Notes:**\r\rImpact on the Confidentiality, Integrity and Availability of the vulnerable component:\r\rConfidentiality: Code execution happens within the impacted component, in this case langchain-experimental, so all resources are necessarily accessible.\r\rIntegrity: There is nothing protected by the impacted component inherently. Although anything returned from the component counts as \u0027information\u0027 for which the trustworthiness can be compromised.\r\rAvailability: The loss of availability isn\u0027t caused by the attack itself, but it happens as a result during the attacker\u0027s post-exploitation steps.\r\r\rImpact on the Confidentiality, Integrity and Availability of the subsequent system:\r\rAs a legitimate low-privileged user of the package (PR:L) the attacker does not have more access to data owned by the package as a result of this vulnerability than they did with normal usage (e.g. can query the DB). The unintended action that one can perform by breaking out of the app environment and exfiltrating files, making remote connections etc. happens during the post exploitation phase in the subsequent system - in this case, the OS.\r\rAT:P: An attacker needs to be able to influence the input prompt, whilst the server is configured with the VectorSQLDatabaseChain plugin."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:H/E:P",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "Arbitrary Code Execution",
"lang": "en"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-07-15T05:00:04.083Z",
"orgId": "bae035ff-b466-4ff4-94d0-fc9efd9e1730",
"shortName": "snyk"
},
"references": [
{
"url": "https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAINEXPERIMENTAL-7278171"
},
{
"url": "https://github.com/langchain-ai/langchain/blob/672907bbbb7c38bf19787b78e4ffd7c8a9026fe4/libs/experimental/langchain_experimental/sql/vector_sql.py%23L81"
},
{
"url": "https://github.com/langchain-ai/langchain/commit/7b13292e3544b2f5f2bfb8a27a062ea2b0c34561"
}
]
}
},
"cveMetadata": {
"assignerOrgId": "bae035ff-b466-4ff4-94d0-fc9efd9e1730",
"assignerShortName": "snyk",
"cveId": "CVE-2024-21513",
"datePublished": "2024-07-15T05:00:04.083Z",
"dateReserved": "2023-12-22T12:33:20.120Z",
"dateUpdated": "2024-08-01T22:20:40.879Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-38459 (GCVE-0-2024-38459)
Vulnerability from nvd – Published: 2024-06-16 00:00 – Updated: 2024-08-02 04:12
VLAI
EPSS
VEX
Summary
langchain_experimental (aka LangChain Experimental) before 0.0.61 for LangChain provides Python REPL access without an opt-in step. NOTE; this issue exists because of an incomplete fix for CVE-2024-27444.
Severity
7.8 (High)
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- n/a
- CWE-276 - Incorrect Default Permissions
Assigner
References
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| langchain | langchain_experimental |
Affected:
0 , < 0.0.61
(custom)
cpe:2.3:a:langchain:langchain_experimental:-:*:*:*:*:*:*:* |
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain:langchain_experimental:-:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "langchain_experimental",
"vendor": "langchain",
"versions": [
{
"lessThan": "0.0.61",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 7.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
}
},
{
"other": {
"content": {
"id": "CVE-2024-38459",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-06-17T14:06:24.353580Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-276",
"description": "CWE-276 Incorrect Default Permissions",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-06-17T14:16:10.505Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
},
{
"providerMetadata": {
"dateUpdated": "2024-08-02T04:12:24.595Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/pull/22860"
},
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/commit/ce0b0f22a175139df8f41cdcfb4d2af411112009"
},
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/compare/langchain-experimental==0.0.60...langchain-experimental==0.0.61"
}
],
"title": "CVE Program Container"
}
],
"cna": {
"affected": [
{
"product": "n/a",
"vendor": "n/a",
"versions": [
{
"status": "affected",
"version": "n/a"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "langchain_experimental (aka LangChain Experimental) before 0.0.61 for LangChain provides Python REPL access without an opt-in step. NOTE; this issue exists because of an incomplete fix for CVE-2024-27444."
}
],
"problemTypes": [
{
"descriptions": [
{
"description": "n/a",
"lang": "en",
"type": "text"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-06-16T14:46:44.457Z",
"orgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"shortName": "mitre"
},
"references": [
{
"url": "https://github.com/langchain-ai/langchain/pull/22860"
},
{
"url": "https://github.com/langchain-ai/langchain/commit/ce0b0f22a175139df8f41cdcfb4d2af411112009"
},
{
"url": "https://github.com/langchain-ai/langchain/compare/langchain-experimental==0.0.60...langchain-experimental==0.0.61"
}
]
}
},
"cveMetadata": {
"assignerOrgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"assignerShortName": "mitre",
"cveId": "CVE-2024-38459",
"datePublished": "2024-06-16T00:00:00.000Z",
"dateReserved": "2024-06-16T00:00:00.000Z",
"dateUpdated": "2024-08-02T04:12:24.595Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-27444 (GCVE-0-2024-27444)
Vulnerability from nvd – Published: 2024-02-26 00:00 – Updated: 2024-08-06 15:13
VLAI
EPSS
VEX
Summary
langchain_experimental (aka LangChain Experimental) in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the __import__, __subclasses__, __builtins__, __globals__, __getattribute__, __bases__, __mro__, or __base__ attribute in Python code. These are not prohibited by pal_chain/base.py.
Severity
9.8 (Critical)
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- n/a
- CWE-749 - Exposed Dangerous Method or Function
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| langchain | langchain_experimental |
Affected:
0 , < 0.1.8
(custom)
cpe:2.3:a:langchain:langchain_experimental:*:*:*:*:*:python:*:* |
{
"containers": {
"adp": [
{
"providerMetadata": {
"dateUpdated": "2024-08-02T00:34:52.332Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/commit/de9a6cdf163ed00adaf2e559203ed0a9ca2f1de7"
}
],
"title": "CVE Program Container"
},
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain:langchain_experimental:*:*:*:*:*:python:*:*"
],
"defaultStatus": "unknown",
"product": "langchain_experimental",
"vendor": "langchain",
"versions": [
{
"lessThan": "0.1.8",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
},
{
"other": {
"content": {
"id": "CVE-2024-27444",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-08-06T13:45:35.709205Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-749",
"description": "CWE-749 Exposed Dangerous Method or Function",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-08-06T15:13:44.695Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "n/a",
"vendor": "n/a",
"versions": [
{
"status": "affected",
"version": "n/a"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "langchain_experimental (aka LangChain Experimental) in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the __import__, __subclasses__, __builtins__, __globals__, __getattribute__, __bases__, __mro__, or __base__ attribute in Python code. These are not prohibited by pal_chain/base.py."
}
],
"problemTypes": [
{
"descriptions": [
{
"description": "n/a",
"lang": "en",
"type": "text"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-02-26T04:43:53.062Z",
"orgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"shortName": "mitre"
},
"references": [
{
"url": "https://github.com/langchain-ai/langchain/commit/de9a6cdf163ed00adaf2e559203ed0a9ca2f1de7"
}
]
}
},
"cveMetadata": {
"assignerOrgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"assignerShortName": "mitre",
"cveId": "CVE-2024-27444",
"datePublished": "2024-02-26T00:00:00.000Z",
"dateReserved": "2024-02-26T00:00:00.000Z",
"dateUpdated": "2024-08-06T15:13:44.695Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-46946 (GCVE-0-2024-46946)
Vulnerability from cvelistv5 – Published: 2024-09-19 00:00 – Updated: 2024-09-19 14:06
VLAI
EPSS
VEX
Summary
langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 (2023-10-05).
Severity
9.8 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- n/a
- CWE-20 - Improper Input Validation
Assigner
References
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| langchain | langchain_experimental |
Affected:
0.1.17 , ≤ 0.3.0
(custom)
cpe:2.3:a:langchain:langchain_experimental:*:*:*:*:*:python:*:* |
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain:langchain_experimental:*:*:*:*:*:python:*:*"
],
"defaultStatus": "unknown",
"product": "langchain_experimental",
"vendor": "langchain",
"versions": [
{
"lessThanOrEqual": "0.3.0",
"status": "affected",
"version": "0.1.17",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
},
{
"other": {
"content": {
"id": "CVE-2024-46946",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-09-19T14:04:46.354291Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-20",
"description": "CWE-20 Improper Input Validation",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-09-19T14:06:52.692Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "n/a",
"vendor": "n/a",
"versions": [
{
"status": "affected",
"version": "n/a"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain allows attackers to execute arbitrary code through sympy.sympify (which uses eval) in LLMSymbolicMathChain. LLMSymbolicMathChain was introduced in fcccde406dd9e9b05fc9babcbeb9ff527b0ec0c6 (2023-10-05)."
}
],
"problemTypes": [
{
"descriptions": [
{
"description": "n/a",
"lang": "en",
"type": "text"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-09-19T05:03:25.650Z",
"orgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"shortName": "mitre"
},
"references": [
{
"url": "https://cwe.mitre.org/data/definitions/95.html"
},
{
"url": "https://github.com/langchain-ai/langchain/releases/tag/langchain-experimental%3D%3D0.3.0"
},
{
"url": "https://docs.sympy.org/latest/modules/codegen.html"
},
{
"url": "https://gist.github.com/12end/68c0c58d2564ef4141bccd4651480820#file-cve-2024-46946-txt"
}
]
}
},
"cveMetadata": {
"assignerOrgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"assignerShortName": "mitre",
"cveId": "CVE-2024-46946",
"datePublished": "2024-09-19T00:00:00.000Z",
"dateReserved": "2024-09-15T00:00:00.000Z",
"dateUpdated": "2024-09-19T14:06:52.692Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-21513 (GCVE-0-2024-21513)
Vulnerability from cvelistv5 – Published: 2024-07-15 05:00 – Updated: 2024-08-01 22:20
VLAI
EPSS
VEX
Summary
Versions of the package langchain-experimental from 0.0.15 and before 0.0.21 are vulnerable to Arbitrary Code Execution when retrieving values from the database, the code will attempt to call 'eval' on all values. An attacker can exploit this vulnerability and execute arbitrary python code if they can control the input prompt and the server is configured with VectorSQLDatabaseChain.
**Notes:**
Impact on the Confidentiality, Integrity and Availability of the vulnerable component:
Confidentiality: Code execution happens within the impacted component, in this case langchain-experimental, so all resources are necessarily accessible.
Integrity: There is nothing protected by the impacted component inherently. Although anything returned from the component counts as 'information' for which the trustworthiness can be compromised.
Availability: The loss of availability isn't caused by the attack itself, but it happens as a result during the attacker's post-exploitation steps.
Impact on the Confidentiality, Integrity and Availability of the subsequent system:
As a legitimate low-privileged user of the package (PR:L) the attacker does not have more access to data owned by the package as a result of this vulnerability than they did with normal usage (e.g. can query the DB). The unintended action that one can perform by breaking out of the app environment and exfiltrating files, making remote connections etc. happens during the post exploitation phase in the subsequent system - in this case, the OS.
AT:P: An attacker needs to be able to influence the input prompt, whilst the server is configured with the VectorSQLDatabaseChain plugin.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
Impacted products
2 products
| Vendor | Product | Version | |
|---|---|---|---|
| n/a | langchain-experimental |
Affected:
0.0.15 , < 0.0.21
(semver)
|
|
| langchain | langchain_experimental |
Affected:
0.0.15 , < 0.0.21
(custom)
cpe:2.3:a:langchain:langchain_experimental:0.0.15:*:*:*:*:python:*:* |
Credits
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain:langchain_experimental:0.0.15:*:*:*:*:python:*:*"
],
"defaultStatus": "unknown",
"product": "langchain_experimental",
"vendor": "langchain",
"versions": [
{
"lessThan": "0.0.21",
"status": "affected",
"version": "0.0.15",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-21513",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-07-15T19:05:37.533971Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94 Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-07-15T19:10:56.283Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
},
{
"providerMetadata": {
"dateUpdated": "2024-08-01T22:20:40.879Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"tags": [
"x_transferred"
],
"url": "https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAINEXPERIMENTAL-7278171"
},
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/blob/672907bbbb7c38bf19787b78e4ffd7c8a9026fe4/libs/experimental/langchain_experimental/sql/vector_sql.py%23L81"
},
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/commit/7b13292e3544b2f5f2bfb8a27a062ea2b0c34561"
}
],
"title": "CVE Program Container"
}
],
"cna": {
"affected": [
{
"product": "langchain-experimental",
"vendor": "n/a",
"versions": [
{
"lessThan": "0.0.21",
"status": "affected",
"version": "0.0.15",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"value": "Rory McNamara (Snyk Security Research)"
}
],
"descriptions": [
{
"lang": "en",
"value": "Versions of the package langchain-experimental from 0.0.15 and before 0.0.21 are vulnerable to Arbitrary Code Execution when retrieving values from the database, the code will attempt to call \u0027eval\u0027 on all values. An attacker can exploit this vulnerability and execute arbitrary python code if they can control the input prompt and the server is configured with VectorSQLDatabaseChain.\r\r**Notes:**\r\rImpact on the Confidentiality, Integrity and Availability of the vulnerable component:\r\rConfidentiality: Code execution happens within the impacted component, in this case langchain-experimental, so all resources are necessarily accessible.\r\rIntegrity: There is nothing protected by the impacted component inherently. Although anything returned from the component counts as \u0027information\u0027 for which the trustworthiness can be compromised.\r\rAvailability: The loss of availability isn\u0027t caused by the attack itself, but it happens as a result during the attacker\u0027s post-exploitation steps.\r\r\rImpact on the Confidentiality, Integrity and Availability of the subsequent system:\r\rAs a legitimate low-privileged user of the package (PR:L) the attacker does not have more access to data owned by the package as a result of this vulnerability than they did with normal usage (e.g. can query the DB). The unintended action that one can perform by breaking out of the app environment and exfiltrating files, making remote connections etc. happens during the post exploitation phase in the subsequent system - in this case, the OS.\r\rAT:P: An attacker needs to be able to influence the input prompt, whilst the server is configured with the VectorSQLDatabaseChain plugin."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:H/E:P",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "Arbitrary Code Execution",
"lang": "en"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-07-15T05:00:04.083Z",
"orgId": "bae035ff-b466-4ff4-94d0-fc9efd9e1730",
"shortName": "snyk"
},
"references": [
{
"url": "https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAINEXPERIMENTAL-7278171"
},
{
"url": "https://github.com/langchain-ai/langchain/blob/672907bbbb7c38bf19787b78e4ffd7c8a9026fe4/libs/experimental/langchain_experimental/sql/vector_sql.py%23L81"
},
{
"url": "https://github.com/langchain-ai/langchain/commit/7b13292e3544b2f5f2bfb8a27a062ea2b0c34561"
}
]
}
},
"cveMetadata": {
"assignerOrgId": "bae035ff-b466-4ff4-94d0-fc9efd9e1730",
"assignerShortName": "snyk",
"cveId": "CVE-2024-21513",
"datePublished": "2024-07-15T05:00:04.083Z",
"dateReserved": "2023-12-22T12:33:20.120Z",
"dateUpdated": "2024-08-01T22:20:40.879Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-38459 (GCVE-0-2024-38459)
Vulnerability from cvelistv5 – Published: 2024-06-16 00:00 – Updated: 2024-08-02 04:12
VLAI
EPSS
VEX
Summary
langchain_experimental (aka LangChain Experimental) before 0.0.61 for LangChain provides Python REPL access without an opt-in step. NOTE; this issue exists because of an incomplete fix for CVE-2024-27444.
Severity
7.8 (High)
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- n/a
- CWE-276 - Incorrect Default Permissions
Assigner
References
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| langchain | langchain_experimental |
Affected:
0 , < 0.0.61
(custom)
cpe:2.3:a:langchain:langchain_experimental:-:*:*:*:*:*:*:* |
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain:langchain_experimental:-:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "langchain_experimental",
"vendor": "langchain",
"versions": [
{
"lessThan": "0.0.61",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 7.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
}
},
{
"other": {
"content": {
"id": "CVE-2024-38459",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-06-17T14:06:24.353580Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-276",
"description": "CWE-276 Incorrect Default Permissions",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-06-17T14:16:10.505Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
},
{
"providerMetadata": {
"dateUpdated": "2024-08-02T04:12:24.595Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/pull/22860"
},
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/commit/ce0b0f22a175139df8f41cdcfb4d2af411112009"
},
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/compare/langchain-experimental==0.0.60...langchain-experimental==0.0.61"
}
],
"title": "CVE Program Container"
}
],
"cna": {
"affected": [
{
"product": "n/a",
"vendor": "n/a",
"versions": [
{
"status": "affected",
"version": "n/a"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "langchain_experimental (aka LangChain Experimental) before 0.0.61 for LangChain provides Python REPL access without an opt-in step. NOTE; this issue exists because of an incomplete fix for CVE-2024-27444."
}
],
"problemTypes": [
{
"descriptions": [
{
"description": "n/a",
"lang": "en",
"type": "text"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-06-16T14:46:44.457Z",
"orgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"shortName": "mitre"
},
"references": [
{
"url": "https://github.com/langchain-ai/langchain/pull/22860"
},
{
"url": "https://github.com/langchain-ai/langchain/commit/ce0b0f22a175139df8f41cdcfb4d2af411112009"
},
{
"url": "https://github.com/langchain-ai/langchain/compare/langchain-experimental==0.0.60...langchain-experimental==0.0.61"
}
]
}
},
"cveMetadata": {
"assignerOrgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"assignerShortName": "mitre",
"cveId": "CVE-2024-38459",
"datePublished": "2024-06-16T00:00:00.000Z",
"dateReserved": "2024-06-16T00:00:00.000Z",
"dateUpdated": "2024-08-02T04:12:24.595Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-27444 (GCVE-0-2024-27444)
Vulnerability from cvelistv5 – Published: 2024-02-26 00:00 – Updated: 2024-08-06 15:13
VLAI
EPSS
VEX
Summary
langchain_experimental (aka LangChain Experimental) in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the __import__, __subclasses__, __builtins__, __globals__, __getattribute__, __bases__, __mro__, or __base__ attribute in Python code. These are not prohibited by pal_chain/base.py.
Severity
9.8 (Critical)
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- n/a
- CWE-749 - Exposed Dangerous Method or Function
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| langchain | langchain_experimental |
Affected:
0 , < 0.1.8
(custom)
cpe:2.3:a:langchain:langchain_experimental:*:*:*:*:*:python:*:* |
{
"containers": {
"adp": [
{
"providerMetadata": {
"dateUpdated": "2024-08-02T00:34:52.332Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"tags": [
"x_transferred"
],
"url": "https://github.com/langchain-ai/langchain/commit/de9a6cdf163ed00adaf2e559203ed0a9ca2f1de7"
}
],
"title": "CVE Program Container"
},
{
"affected": [
{
"cpes": [
"cpe:2.3:a:langchain:langchain_experimental:*:*:*:*:*:python:*:*"
],
"defaultStatus": "unknown",
"product": "langchain_experimental",
"vendor": "langchain",
"versions": [
{
"lessThan": "0.1.8",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
},
{
"other": {
"content": {
"id": "CVE-2024-27444",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-08-06T13:45:35.709205Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-749",
"description": "CWE-749 Exposed Dangerous Method or Function",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-08-06T15:13:44.695Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "n/a",
"vendor": "n/a",
"versions": [
{
"status": "affected",
"version": "n/a"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "langchain_experimental (aka LangChain Experimental) in LangChain before 0.1.8 allows an attacker to bypass the CVE-2023-44467 fix and execute arbitrary code via the __import__, __subclasses__, __builtins__, __globals__, __getattribute__, __bases__, __mro__, or __base__ attribute in Python code. These are not prohibited by pal_chain/base.py."
}
],
"problemTypes": [
{
"descriptions": [
{
"description": "n/a",
"lang": "en",
"type": "text"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-02-26T04:43:53.062Z",
"orgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"shortName": "mitre"
},
"references": [
{
"url": "https://github.com/langchain-ai/langchain/commit/de9a6cdf163ed00adaf2e559203ed0a9ca2f1de7"
}
]
}
},
"cveMetadata": {
"assignerOrgId": "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
"assignerShortName": "mitre",
"cveId": "CVE-2024-27444",
"datePublished": "2024-02-26T00:00:00.000Z",
"dateReserved": "2024-02-26T00:00:00.000Z",
"dateUpdated": "2024-08-06T15:13:44.695Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}