CVE-2026-25481

CRITICAL

9.6

Description

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.59.32, there is a bypass to the fix for CVE-2025-46724. TableChatAgent can call pandas_eval tool to evaluate the expression. There is a WAF in langroid/utils/pandas_utils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to _literal_ok() returning False instead of raising UnsafeCommandError on invalid input, combined with unrestricted access to dangerous dunder attributes (__init__, __globals__, __builtins__). This allows chaining whitelisted DataFrame methods to leak the eval builtin and execute arbitrary code. This issue has been patched in version 0.59.32.

CVE Details

CVSS v3.1 Score9.6

SeverityCRITICAL

CVSS VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredNONE

User InteractionREQUIRED

Published2/4/2026

Last Modified2/20/2026

Sourcenvd

Honeypot Sightings0

Affected Products

langroid:langroid

Weaknesses (CWE)

CWE-94

References

https://github.com/langroid/langroid/commit/30abbc1a854dee22fbd2f8b2f575dfdabdb603ea(security-advisories@github.com)

https://github.com/langroid/langroid/security/advisories/GHSA-jqq5-wc57-f8hj(security-advisories@github.com)

https://github.com/langroid/langroid/security/advisories/GHSA-x34r-63hx-w57f(security-advisories@github.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.