Langroid has a Code Injection vulnerability in TableChatAgent
Critical severity
GitHub Reviewed
Published
May 20, 2025
in
langroid/langroid
•
Updated May 20, 2025
Description
Published to the GitHub Advisory Database
May 20, 2025
Reviewed
May 20, 2025
Published by the National Vulnerability Database
May 20, 2025
Last updated
May 20, 2025
Summary
TableChatAgent
uses pandas eval(). If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection.PoC
For example, one could prompt the Agent:
...to read the contents of the host filesystem.
Impact
Confidentiality, Integrity and Availability of the system hosting the LLM application.
Fix
Langroid 0.53.15 sanitizes input to
TableChatAgent
by default to tackle the most common attack vectors, and added several warnings about the risky behavior in the project documentation.References