CVE-2026-25481

critical

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.

References

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

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

https://github.com/langroid/langroid/commit/30abbc1a854dee22fbd2f8b2f575dfdabdb603ea

Details

Source: Mitre, NVD

Published: 2026-02-04

Updated: 2026-02-20

Risk Information

CVSS v2

Base Score: 10

Vector: CVSS2#AV:N/AC:L/Au:N/C:C/I:C/A:C

Severity: Critical

CVSS v3

Base Score: 9.6

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

Severity: Critical

CVSS v4

Base Score: 9.4

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

Severity: Critical

EPSS

EPSS: 0.00067