Vulnerability details
CVE-2026-25481
Langroid has WAF Bypass Leading to RCE in TableChatAgent
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.
CVSS scores
| Score | Version | Source | Vector |
|---|---|---|---|
| 9.4Critical | 4.0 | CVEProject cvelistV5 (CNA) (GitHub_M) | 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 |
Affected products
| Vendor | Product | Versions | Source |
|---|---|---|---|
| langroid | langroid | < 0.59.32 | CVEProject cvelistV5 (CNA) |
References and advisories
3Details
- Published
- 2026-02-04
- Last updated
- 2026-02-05
- State
- Published
- Assigner (CNA)
- GitHub_M
Exploit prediction (EPSS)
SSVC assessment (CISA)
- Automatable
- Yes
- Exploitation
- Proof of concept
- Technical impact
- Total
Weaknesses (CWE)
- CWE-94Improper Control of Generation of Code ('Code Injection')