PyPI: langroid
CVE-2025-46724
Safety vulnerability ID: SFTY-20250520-23009
Safety legacy ID: pyup.io-77310
Affected versions of Langroid are vulnerable to Code Injection when using TableChatAgent. TableChatAgent uses pandas eval(). If fed by untrusted user input, like the case of a public-facing LLM application, an attacker may be able to make the agent run malicious commands compromising the host system.
Overview
Langroid has a Code Injection vulnerability in TableChatAgent
Advisory
Affected versions of Langroid are vulnerable to Code Injection when using TableChatAgent. TableChatAgent uses pandas eval(). If fed by untrusted user input, like the case of a public-facing LLM application, an attacker may be able to make the agent run malicious commands compromising the host system.
How to Fix
Mitigation and Workarounds
---
Vulnerable Functions
Functions linked to known vulnerabilities.
References
- https://getsafety.com/vulnerabilities/SFTY-20250520-23009/CVE-2025-46724
- https://github.com/langroid/langroid/security/advisories/GHSA-jqq5-wc57-f8hj
- https://github.com/langroid/langroid/commit/0d9e4a7bb3ae2eef8d38f2e970ff916599a2b2a6
- https://nvd.nist.gov/vuln/detail/CVE-2025-46724
- https://github.com/pypa/advisory-database/tree/main/vulns/langroid/PYSEC-2026-381.yaml
- https://pypi.org/project/langroid
- https://github.com/advisories/GHSA-jqq5-wc57-f8hj
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