CVE-2026-104873: langchain-ai langgraph Incorrect Authorization

Vulnerability summary

CVE-2026-104873 is a high (CVSS 7.6) Incorrect Authorization vulnerability in langchain-ai langgraph. EPSS estimates a 0.25% chance of exploitation in the next 30 days, higher than 15.7% of scored vulnerabilities.

Timeline

1. 02-10-2026
   PublishedVulnerability first disclosed.
2. 05-10-2026
   Last modifiedVulnerability information updated.

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.

• CWE-863Incorrect AuthorizationThe product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check.