CVE-2026-55236: CWE-285: Improper Authorization in langchain-ai langgraph-api
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.
AI Analysis
Technical Summary
The langgraph-api component of langchain-ai implements an API for rapid development and testing. Before version 0.10.0, the run-creation endpoint authorizes assistants by dispatching the assistants.search event, which is incomplete compared to the assistants.read event used elsewhere. In deployments with custom authorization handlers that only handle assistants.read and omit assistants.search, no owner filter is applied during run creation. This allows a low-privileged user to reference and execute runs using another user's private assistant, exposing sensitive metadata, configuration, and context. The issue is resolved in langgraph-api version 0.10.0.
Potential Impact
An attacker with low privileges can access and execute runs using another user's private assistant, potentially disclosing sensitive metadata, configuration, and context. This could lead to unauthorized information disclosure and limited integrity impact by executing runs with another assistant's configuration. Availability is not affected.
Mitigation Recommendations
This vulnerability is fixed in langgraph-api version 0.10.0. Users should upgrade to version 0.10.0 or later to remediate this issue. Deployments that have custom authorization handlers applying an owner filter to all assistant events or a global fallback handler are not affected. Patch status is confirmed fixed in 0.10.0.
CVE-2026-55236: CWE-285: Improper Authorization in langchain-ai langgraph-api
Description
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.
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 component of langchain-ai implements an API for rapid development and testing. Before version 0.10.0, the run-creation endpoint authorizes assistants by dispatching the assistants.search event, which is incomplete compared to the assistants.read event used elsewhere. In deployments with custom authorization handlers that only handle assistants.read and omit assistants.search, no owner filter is applied during run creation. This allows a low-privileged user to reference and execute runs using another user's private assistant, exposing sensitive metadata, configuration, and context. The issue is resolved in langgraph-api version 0.10.0.
Potential Impact
An attacker with low privileges can access and execute runs using another user's private assistant, potentially disclosing sensitive metadata, configuration, and context. This could lead to unauthorized information disclosure and limited integrity impact by executing runs with another assistant's configuration. Availability is not affected.
Mitigation Recommendations
This vulnerability is fixed in langgraph-api version 0.10.0. Users should upgrade to version 0.10.0 or later to remediate this issue. Deployments that have custom authorization handlers applying an owner filter to all assistant events or a global fallback handler are not affected. Patch status is confirmed fixed in 0.10.0.
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: 6aa81a7c55bf5e2cf54846cc
Added to database: 09/14/2026, 16:02:04 UTC
Last enriched: 09/14/2026, 16:16:35 UTC
Last updated: 09/15/2026, 06:04:25 UTC
Views: 19
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.