CVE-2026-55236 json
langgraph-api: Incomplete assistant authorization in LangGraph Server run creation
published 2mo ago modified 14d ago also GHSA-jfj5-wrj9-63x4 , PYSEC-2026-3858 , EUVD-2026-77583
- cvss
- 5.9
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.3%
- EPSS 0.3% chance of exploitation in 30 days, percentile 17%
- public exploits
- 0
- none known
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.
Patch / fix
- pypi langgraph-api 0.10.0
Is CVE-2026-55236 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerCISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
- Assessed
- last mo.
Exploit prediction
0.26% chance of exploitation in the next 30 days, higher than 17% of all scored CVEs (FIRST EPSS, 2026-11-11).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 5.9 | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:N |
| GitHub | 3.1 | 5.9 | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:N |
| OSV | 3.1 | 5.9 | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:N |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | langgraph-api | <0.10.0 |
0.10.0 |
Affected products
- langchain-ai langgraph-api
Classification
- Weakness
-
- CWE-285 Improper Authorization
References
-
github.com
/langchain-ai/helm/security/advisories/GHSA-jfj5-wrj9-63x4
web
-
github.com
/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx
web
-
nvd.nist.gov
/vuln/detail/CVE-2026-55236
advisory
-
github.com
/langchain-ai/helm
package
-
github.com
/pypa/advisory-database/tree/main/vulns/langgraph-api/PYSEC-2026-3858.yaml
web
-
pypi.org
/project/langgraph-api
package
-
github.com
/advisories/GHSA-jfj5-wrj9-63x4
advisory
Sources
- CVE List CVE-2026-55236
- GitHub Advisory GHSA-jfj5-wrj9-63x4
- NVD CVE-2026-55236
- OSV PYSEC-2026-3858
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.