Vulnerability CVE-2023-29374
Published: 2023-04-05

Description:
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec method.

 References:
https://twitter.com/rharang/status/1641899743608463365/photo/1
https://github.com/hwchase17/langchain/pull/1119
https://github.com/hwchase17/langchain/issues/814
https://github.com/hwchase17/langchain/issues/1026
Copyright 2026, cxsecurity.com

 

Back to Top