CVE-2026-55236
Received Received - Intake

Authorization Bypass in LangGraph API Prior to 0.10.0

Publication date: 2026-09-14

Last updated on: 2026-09-14

Assigner: GitHub, Inc.

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 Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-09-14
Last Modified
2026-09-14
Generated
2026-09-15
AI Q&A
2026-09-14
EPSS Evaluated
N/A
NVD
CVE-2026-55236
EUVD
EUVD-2026-77583

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
langgraph langgraph-api 0.10.0
langgraph-ai langgraph-api to 0.10.0 (exc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-285 The product does not perform or incorrectly performs an authorization check when an actor attempts to access a resource or perform an action.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability is an authorization bypass in the LangGraph API run-creation process. In versions before 0.10.0, the system used an incomplete authorization check (assistants.search) instead of the proper check (assistants.read) when creating runs. This allowed low-privileged users to reference and access private assistants owned by other users if the deployment lacked a global fallback handler or an assistants.search handler.

Detection Guidance

To detect this vulnerability, check if your langgraph-api version is below 0.10.0. Run: npm list langgraph-api or pip show langgraph-api. If the version is older, the system may be vulnerable. Review authorization handler configurations for assistants.search and assistants.read events. Ensure handlers cover all assistant-related events or have a global fallback.

Impact Analysis

An attacker could create a run that references another user's private assistant, exposing sensitive metadata, configuration, and context. The run could also execute using the private assistant's configuration, potentially leading to unauthorized actions or data exposure. This primarily affects confidentiality and integrity.

Compliance Impact

This vulnerability could lead to unauthorized access to private data, violating confidentiality requirements in GDPR and HIPAA. Exposure of sensitive metadata and assistant configurations may result in non-compliance with data protection regulations, potentially leading to legal and regulatory penalties.

Mitigation Strategies

Upgrade langgraph-api to version 0.10.0 or later immediately. Update custom authorization handlers to include assistants.search or implement a global handler covering all assistant events. Verify that owner filters are applied consistently across all assistant-related paths to prevent unauthorized access.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-55236. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart