CVE-2026-55235: CWE-287: Improper Authentication in langchain-ai langgraph-api
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.
AI Analysis
Technical Summary
The langgraph-api prior to version 0.10.0 allows webhook targets to specify relative URLs delivered via an in-process loopback transport. The authentication middleware treats this loopback transport as internal and does not apply the authentication context used for external requests. In deployments relying on per-user authorization boundaries, this flaw enables an authenticated user to direct a webhook to the server's own thread and run routes, thereby creating or modifying runs on other users' threads and incorporating metadata from those threads. The vulnerability requires webhook targets and per-user authorization to be in use. The issue is resolved in version 0.10.0.
Potential Impact
An authenticated user can bypass intended per-user authorization boundaries by exploiting the loopback transport webhook delivery mechanism. This allows unauthorized creation or modification of runs on other users' threads and limited incorporation of their metadata. The impact includes unauthorized modification of data (integrity) and limited availability impact. Confidentiality is not affected.
Mitigation Recommendations
Upgrade langgraph-api to version 0.10.0 or later where this issue is fixed. Deployments that deliberately enable loopback delivery should restrict it strictly to controlled same-process routes to avoid unauthenticated webhook requests. No other mitigations are indicated.
CVE-2026-55235: CWE-287: Improper Authentication in langchain-ai langgraph-api
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.
CVSS v3.1
Score 5.9medium
Affected software
langchain-ai
langgraph-api
pkg:github/langchain-ai/langgraph-apiRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The langgraph-api prior to version 0.10.0 allows webhook targets to specify relative URLs delivered via an in-process loopback transport. The authentication middleware treats this loopback transport as internal and does not apply the authentication context used for external requests. In deployments relying on per-user authorization boundaries, this flaw enables an authenticated user to direct a webhook to the server's own thread and run routes, thereby creating or modifying runs on other users' threads and incorporating metadata from those threads. The vulnerability requires webhook targets and per-user authorization to be in use. The issue is resolved in version 0.10.0.
Potential Impact
An authenticated user can bypass intended per-user authorization boundaries by exploiting the loopback transport webhook delivery mechanism. This allows unauthorized creation or modification of runs on other users' threads and limited incorporation of their metadata. The impact includes unauthorized modification of data (integrity) and limited availability impact. Confidentiality is not affected.
Mitigation Recommendations
Upgrade langgraph-api to version 0.10.0 or later where this issue is fixed. Deployments that deliberately enable loopback delivery should restrict it strictly to controlled same-process routes to avoid unauthenticated webhook requests. No other mitigations are indicated.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-06-16T16:44:00.623Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6aa81a7c55bf5e2cf54846c7
Added to database: 09/14/2026, 16:02:04 UTC
Last enriched: 09/14/2026, 16:17:01 UTC
Last updated: 09/15/2026, 05:10:50 UTC
Views: 12
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.