Search
Find a vulnerability
Search criteria
4 vulnerabilities found for langgraph-api by langchain-ai
CVE-2026-55236 (GCVE-0-2026-55236)
Vulnerability from nvd – Published: 2026-09-14 15:51 – Updated: 2026-09-14 16:42
VLAI
EPSS
VEX
Title
langgraph-api: Incomplete assistant authorization in LangGraph Server run creation
Summary
langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, the langgraph-api run-creation path authorizes the assistant attached to a run by dispatching assistants.search with an incomplete value instead of the assistants.read event used by direct reads and cron creation. In deployments with custom resource handlers that register only assistants.read, omit an assistants.search handler, and have no global fallback handler, no applicable handler supplies an owner filter, allowing a low-privileged user to reference another user's private assistant through POST /runs or POST /threads/{thread_id}/runs. The run-creation response can disclose the private assistant's metadata, config, and context, and the run can execute using that assistant's configuration. Deployments without custom authorization handlers, or with an equivalent owner filter applied through a global handler or across all assistant events, are not affected. This issue is fixed in version 0.10.0.
Severity
5.9 (Medium)
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-14 16:41 UTC
CWE
- CWE-285 - Improper Authorization
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/langchain-ai/helm/security/adv… | x_refsource_CONFIRM |
| https://github.com/langchain-ai/docs/blob/7b70fba… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| langchain-ai | langgraph-api |
Affected:
< 0.10.0
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-55236",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-14T16:41:45.325753Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-14T16:42:03.499Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langgraph-api",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.10.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, the langgraph-api run-creation path authorizes the assistant attached to a run by dispatching assistants.search with an incomplete value instead of the assistants.read event used by direct reads and cron creation. In deployments with custom resource handlers that register only assistants.read, omit an assistants.search handler, and have no global fallback handler, no applicable handler supplies an owner filter, allowing a low-privileged user to reference another user\u0027s private assistant through POST /runs or POST /threads/{thread_id}/runs. The run-creation response can disclose the private assistant\u0027s metadata, config, and context, and the run can execute using that assistant\u0027s configuration. Deployments without custom authorization handlers, or with an equivalent owner filter applied through a global handler or across all assistant events, are not affected. This issue is fixed in version 0.10.0."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 5.9,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-285",
"description": "CWE-285: Improper Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-14T15:52:18.257Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/helm/security/advisories/GHSA-jfj5-wrj9-63x4",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/helm/security/advisories/GHSA-jfj5-wrj9-63x4"
},
{
"name": "https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx"
}
],
"source": {
"advisory": "GHSA-jfj5-wrj9-63x4",
"discovery": "UNKNOWN"
},
"title": "langgraph-api: Incomplete assistant authorization in LangGraph Server run creation"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55236",
"datePublished": "2026-09-14T15:51:17.118Z",
"dateReserved": "2026-06-16T16:44:00.623Z",
"dateUpdated": "2026-09-14T16:42:03.499Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-55235 (GCVE-0-2026-55235)
Vulnerability from nvd – Published: 2026-09-14 15:53 – Updated: 2026-09-14 15:53
VLAI
EPSS
VEX
Title
langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authentication
Summary
langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, langgraph-api permits a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport, and the authentication middleware treats that transport as internal without applying the authentication context used for external requests. In deployments that rely on per-user authorization to separate threads and runs, an authenticated user can direct a webhook to the server's own thread and run routes, allowing creation of a run on or modification of another user's thread and limited incorporation of the targeted thread's metadata into the created run record. The affected path requires webhook targets and per-user authorization boundaries; deployments that deliberately re-enable loopback delivery should restrict it to controlled same-process routes because those webhooks remain unauthenticated. This issue is fixed in version 0.10.0.
Severity
5.9 (Medium)
CWE
- CWE-287 - Improper Authentication
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/langchain-ai/helm/security/adv… | x_refsource_CONFIRM |
| https://github.com/langchain-ai/docs/blob/7b70fba… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| langchain-ai | langgraph-api |
Affected:
< 0.10.0
|
{
"containers": {
"cna": {
"affected": [
{
"product": "langgraph-api",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.10.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, langgraph-api permits a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport, and the authentication middleware treats that transport as internal without applying the authentication context used for external requests. In deployments that rely on per-user authorization to separate threads and runs, an authenticated user can direct a webhook to the server\u0027s own thread and run routes, allowing creation of a run on or modification of another user\u0027s thread and limited incorporation of the targeted thread\u0027s metadata into the created run record. The affected path requires webhook targets and per-user authorization boundaries; deployments that deliberately re-enable loopback delivery should restrict it to controlled same-process routes because those webhooks remain unauthenticated. This issue is fixed in version 0.10.0."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 5.9,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-287",
"description": "CWE-287: Improper Authentication",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-14T15:53:19.013Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/helm/security/advisories/GHSA-2c9q-c2q9-qgqv",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/helm/security/advisories/GHSA-2c9q-c2q9-qgqv"
},
{
"name": "https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx"
}
],
"source": {
"advisory": "GHSA-2c9q-c2q9-qgqv",
"discovery": "UNKNOWN"
},
"title": "langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authentication"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55235",
"datePublished": "2026-09-14T15:53:19.013Z",
"dateReserved": "2026-06-16T16:44:00.623Z",
"dateUpdated": "2026-09-14T15:53:19.013Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-55235 (GCVE-0-2026-55235)
Vulnerability from cvelistv5 – Published: 2026-09-14 15:53 – Updated: 2026-09-14 15:53
VLAI
EPSS
VEX
Title
langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authentication
Summary
langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, langgraph-api permits a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport, and the authentication middleware treats that transport as internal without applying the authentication context used for external requests. In deployments that rely on per-user authorization to separate threads and runs, an authenticated user can direct a webhook to the server's own thread and run routes, allowing creation of a run on or modification of another user's thread and limited incorporation of the targeted thread's metadata into the created run record. The affected path requires webhook targets and per-user authorization boundaries; deployments that deliberately re-enable loopback delivery should restrict it to controlled same-process routes because those webhooks remain unauthenticated. This issue is fixed in version 0.10.0.
Severity
5.9 (Medium)
CWE
- CWE-287 - Improper Authentication
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/langchain-ai/helm/security/adv… | x_refsource_CONFIRM |
| https://github.com/langchain-ai/docs/blob/7b70fba… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| langchain-ai | langgraph-api |
Affected:
< 0.10.0
|
{
"containers": {
"cna": {
"affected": [
{
"product": "langgraph-api",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.10.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, langgraph-api permits a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport, and the authentication middleware treats that transport as internal without applying the authentication context used for external requests. In deployments that rely on per-user authorization to separate threads and runs, an authenticated user can direct a webhook to the server\u0027s own thread and run routes, allowing creation of a run on or modification of another user\u0027s thread and limited incorporation of the targeted thread\u0027s metadata into the created run record. The affected path requires webhook targets and per-user authorization boundaries; deployments that deliberately re-enable loopback delivery should restrict it to controlled same-process routes because those webhooks remain unauthenticated. This issue is fixed in version 0.10.0."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 5.9,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-287",
"description": "CWE-287: Improper Authentication",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-14T15:53:19.013Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/helm/security/advisories/GHSA-2c9q-c2q9-qgqv",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/helm/security/advisories/GHSA-2c9q-c2q9-qgqv"
},
{
"name": "https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx"
}
],
"source": {
"advisory": "GHSA-2c9q-c2q9-qgqv",
"discovery": "UNKNOWN"
},
"title": "langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authentication"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55235",
"datePublished": "2026-09-14T15:53:19.013Z",
"dateReserved": "2026-06-16T16:44:00.623Z",
"dateUpdated": "2026-09-14T15:53:19.013Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-55236 (GCVE-0-2026-55236)
Vulnerability from cvelistv5 – Published: 2026-09-14 15:51 – Updated: 2026-09-14 16:42
VLAI
EPSS
VEX
Title
langgraph-api: Incomplete assistant authorization in LangGraph Server run creation
Summary
langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, the langgraph-api run-creation path authorizes the assistant attached to a run by dispatching assistants.search with an incomplete value instead of the assistants.read event used by direct reads and cron creation. In deployments with custom resource handlers that register only assistants.read, omit an assistants.search handler, and have no global fallback handler, no applicable handler supplies an owner filter, allowing a low-privileged user to reference another user's private assistant through POST /runs or POST /threads/{thread_id}/runs. The run-creation response can disclose the private assistant's metadata, config, and context, and the run can execute using that assistant's configuration. Deployments without custom authorization handlers, or with an equivalent owner filter applied through a global handler or across all assistant events, are not affected. This issue is fixed in version 0.10.0.
Severity
5.9 (Medium)
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-14 16:41 UTC
CWE
- CWE-285 - Improper Authorization
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/langchain-ai/helm/security/adv… | x_refsource_CONFIRM |
| https://github.com/langchain-ai/docs/blob/7b70fba… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| langchain-ai | langgraph-api |
Affected:
< 0.10.0
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-55236",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-14T16:41:45.325753Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-14T16:42:03.499Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "langgraph-api",
"vendor": "langchain-ai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.10.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, the langgraph-api run-creation path authorizes the assistant attached to a run by dispatching assistants.search with an incomplete value instead of the assistants.read event used by direct reads and cron creation. In deployments with custom resource handlers that register only assistants.read, omit an assistants.search handler, and have no global fallback handler, no applicable handler supplies an owner filter, allowing a low-privileged user to reference another user\u0027s private assistant through POST /runs or POST /threads/{thread_id}/runs. The run-creation response can disclose the private assistant\u0027s metadata, config, and context, and the run can execute using that assistant\u0027s configuration. Deployments without custom authorization handlers, or with an equivalent owner filter applied through a global handler or across all assistant events, are not affected. This issue is fixed in version 0.10.0."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 5.9,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-285",
"description": "CWE-285: Improper Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-14T15:52:18.257Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/langchain-ai/helm/security/advisories/GHSA-jfj5-wrj9-63x4",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/langchain-ai/helm/security/advisories/GHSA-jfj5-wrj9-63x4"
},
{
"name": "https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx"
}
],
"source": {
"advisory": "GHSA-jfj5-wrj9-63x4",
"discovery": "UNKNOWN"
},
"title": "langgraph-api: Incomplete assistant authorization in LangGraph Server run creation"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55236",
"datePublished": "2026-09-14T15:51:17.118Z",
"dateReserved": "2026-06-16T16:44:00.623Z",
"dateUpdated": "2026-09-14T16:42:03.499Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}