CVE-2026-55235 langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authentication
Authenticated users can bypass authorization checks to modify other users' threads via relative webhook targets in LangGraph Server.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-55235?
CVE-2026-55235 is a medium-severity missing authorization vulnerability in langchain-ai langgraph-api, published on 14 Sep 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
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.
Weakness: CWE-287
Which versions are affected by CVE-2026-55235?
3 open source packages ship an affected version, including langgraph-api.
| Package | Affected | Fixed in |
|---|---|---|
langgraph-api PyPI | All versions | 0.10.0 |
langgraph-api PyPI | All versions | 0.10.0 |
langgraph-api PyPI | All versions | 0.10.0 |
How do I fix CVE-2026-55235?
Upgrade langgraph-api to 0.10.0 or later.
Upgrade, and check permissions on every request on the server, not only in the interface. More about Missing authorization.
Is CVE-2026-55235 being exploited?
There is no known exploitation of CVE-2026-55235 in the wild and no public exploit code.
Sources
Also known as GHSA-2c9q-c2q9-qgqv, PYSEC-2026-3857.