GitHub Advisoryadvisory · PyPI
GHSA-22c2-9gwg-mj59 Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store
HIGH
Official page ↗
- Aliases
- CVE-2025-46725
- Ecosystem
- PyPI
- Packages
- langroid
- Severity
- High
- CVSS vector
- CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:U
- Weaknesses
- CWE-94
- Reviewed
- 2025-05-20
Affected packages
• PyPI langroid: < 0.53.15 → fixed in 0.53.15
Description
Summary
LanceDocChatAgent uses pandas eval() through `compute_from_docs()`:
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.
Related
Alias · CVE (1)
- CVE-2025-46725 Langroid is a Python framework to build large language model (LLM)-powered applications. vulnerability
Weakness · CWE (1)
- CWE-94 Improper Control of Generation of Code weakness