PyPI: langroid
CVE-2025-46725
Safety vulnerability ID: SFTY-20250520-40333
Safety legacy ID: pyup.io-77311
Affected versions of Langroid are vulnerable to Code Injection when using LanceDocChatAgent. LanceDocChatAgent uses pandas eval() through compute_from_docs(). As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframe_calc compromising the host system.
Overview
Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store
Advisory
Affected versions of Langroid are vulnerable to Code Injection when using LanceDocChatAgent. LanceDocChatAgent uses pandas eval() through compute_from_docs(). As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframe_calc compromising the host system.
How to Fix
Mitigation and Workarounds
---
Vulnerable Functions
Functions linked to known vulnerabilities.
References
- https://getsafety.com/vulnerabilities/SFTY-20250520-40333/CVE-2025-46725
- https://github.com/langroid/langroid/security/advisories/GHSA-22c2-9gwg-mj59
- https://github.com/langroid/langroid/commit/0d9e4a7bb3ae2eef8d38f2e970ff916599a2b2a6
- https://nvd.nist.gov/vuln/detail/CVE-2025-46725
- https://github.com/advisories/GHSA-22c2-9gwg-mj59
Verified by Safety
Our Cybersecurity Intelligence Team reviewed this vulnerability. We combine public data with our own research to find issues not yet reported to public sources.
Learn more