CVE-2026-104873 | LangChain AI LangGraph up to 0.4.3 Authorization Decorators actions improper authorization

October 2, 2026 Yanac

A vulnerability was found in LangChain AI LangGraph up to 0.4.3. It has been rated as critical. This affects an unknown part of the component Authorization Decorators. Performing a manipulation of the argument actions results in improper authorization.

This vulnerability is reported as CVE-2026-104873. The attack is possible to be carried out remotely. No exploit exists.

Upgrading the affected component is advised.VulDB Recent EntriesRead More