What’s Vulnerable › Vulnerabilities

CVE-2026-104873: LangGraph SDK custom auth silently ignores actions= on resource decorators

• Severity: high (CVSS 7.6 v4.0)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.3% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-10-02 · updated 2026-10-06
• Weakness: CWE-863

Description

LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. From 0.1.45 until 0.4.4, the langgraph-sdk resource-scoped authorization decorators @auth.on.threads, @auth.on.assistants, and @auth.on.crons ignore the actions argument and register the selected handler for every action on the resource. Because that wildcard resource handler is selected before broader fallback handlers, an authenticated user may bypass fallback action, ownership, or permission checks and read, update, or delete another user's resource. Only Python deployments using actions on the affected decorators are vulnerable, and a deployment remains protected when the selected handler independently enforces all required checks for every action it receives. This issue is fixed in version 0.4.4.

Affected products

• langchain-ai langgraph: from 0.1.45, < 0.4.4

References

• https://github.com/langchain-ai/langgraph/commit/5a77be5e8bec1600ad0a865638d88c1368497559
• https://github.com/langchain-ai/langgraph/releases/tag/sdk==0.4.4
• https://github.com/langchain-ai/langgraph/security/advisories/GHSA-fvww-7h3r-vfhp

Get alerted when CVE-2026-104873 or the next vulnerability affects your stack