langgraph-api: Incomplete assistant authorization in LangGraph Server run creation
Key facts
- Attack vector
- Network
- Privileges required
- Low
- User interaction
- None
- Attack complexity
- High
- Impact type
- Security bypass
- Confidentiality · integrity · availability
- High · Low · None
- Fix status
- Fixed
Attack profile from CVSS 3.1 · CNA. Fix status from CNA and GitHub. Impact type from CWE-285.
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| langchain-ai | langgraph-api | before 0.10.0 | 0.10.0 | Patch available | CNA |
| — | langgraph-api (PyPI) | before 0.10.0 | 0.10.0 | Patch available | GHSA-jfj5-wrj9-63x4 |
- langgraph-api Vendorlangchain-ai Affected before 0.10.0 Fixed in 0.10.0 Patch available CNA
- langgraph-api (PyPI) Vendor— Affected before 0.10.0 Fixed in 0.10.0 Patch available GHSA-jfj5-wrj9-63x4
Remediation
- Fix · CNA langgraph-api (langchain-ai) Fixed in 0.10.0
- Fix · GHSA-jfj5-wrj9-63x4 langgraph-api (PyPI) Fixed in 0.10.0 Advisory →
Timeline
- 2026-10-02 Threatist record created from CVE-2026-55236
- 2026-10-03 Alias added: GHSA-jfj5-wrj9-63x4
- 2026-10-28 3 new references · GHSA-jfj5-wrj9-63x4
References
Other 4
- https://github.com/langchain-ai/helm/security/advisories/GHSA-jfj5-wrj9-63x4
- https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx
- https://github.com/langchain-ai/helm
- https://github.com/pypa/advisory-database/tree/main/vulns/langgraph-api/PYSEC-2026-3858.yaml
More langchain-ai vulnerabilities
- TI-2024-31340 langchain_experimental (aka LangChain Experimental) 0.1.17 through 0.3.0 for LangChain… CVSS 3.1CRITICAL 9.8
- TI-2023-20724 An issue in langchain langchain-ai v.0.0.232 and before allows a remote attacker to… CVSS 3.1CRITICAL 9.8
- TI-2023-20706 An issue in LanChain-ai Langchain v.0.0.245 allows a remote attacker to execute arbitrary… CVSS 3.1CRITICAL 9.8
- TI-2023-20166 An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to… CVSS 3.1CRITICAL 9.8
- TI-2023-20136 An issue in LangChain v.0.0.231 allows a remote attacker to execute arbitrary code via the prompt parameter. CVSS 3.1CRITICAL 9.8
- TI-2023-18185 An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a… CVSS 3.1CRITICAL 9.8
Sources
- CVE-2026-55236 · CVE Program
- CVE-2026-55236 · NVD
- FIRST EPSS
- GHSA-jfj5-wrj9-63x4 · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences