CVE-2025-46725

Summary

LanceDocChatAgent uses pandas eval() through computefromdocs():

https://github.com/langroid/langroid/blob/18667ec7e971efc242505196f6518eb19a0abc1c/langroid/vector_store/base.py#L136-L150

As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframe_calc compromising the host system.

Fix 

Langroid 0.53.15 sanitizes input to the affected function by default to tackle the most common attack vectors, and added several warnings about the risky behavior in the project documentation.