Vulnerability · Published Feb 4, 2026 · Assigned by GitHub_M
CVE-2026-25481Langroid has WAF Bypass Leading to RCE in TableChatAgent
Critical 9.4
In plain English
A critical-severity code injection in langroid from langroid. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.7% (higher than 55% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official 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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | langroid | 0.59.32 | GHSA-x34r-63hx-w57f |
| PyPI | langroid | 0.59.32 | PYSEC-2026-383 |
Affected products (as reported)
Weakness: CWE-94 · Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H