Please use LangChain VDP and LangChain Open Source VDP to report security vulnerabilities.
Repository navigation
Security: langchain-ai/deepagents
Security
SECURITY.md
-
Filesystem permission and approval rules may be bypassed through alternate pathsGHSA-47w2-rfrr-wvq8 published
Oct 15, 2026 by vladislav-nechakhinModerate -
Shell approval bypass in deepagents-acp via commands that fail to parseGHSA-459r-276m-w72x published
Oct 13, 2026 by hntrlModerate
Learn more about advisories related to langchain-ai/deepagents in the GitHub Advisory Database