RCE in Langroid

CVE-2026-25481

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.

Vulnerability class: RCE (Remote Code Execution)

EPSS: 0.006 (47.0th percentile) — read the EPSS interpretation.

CVSS v3 metric

CVSS v3 base score 9.6 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H.

Affected products

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2026-25481?
CVE-2026-25481 is a critical-severity vulnerability in Langroid, classified under Code Injection. CVSS score: 9.6/10. Published 2026-02-04.
How severe is CVE-2026-25481?
Critical severity. CVSS v3 base score is 9.6 out of 10.