langroid

CVE-2026-25481

CVE-2026-25481 is a critical-severity code injection vulnerability in langroid (pip), affecting versions <= 0.59.31. It is fixed in 0.59.32.

Key facts
CVSS score
N/A
Critical
Attack vector
Not available
Issuing authority
GitHub Advisory Database
Affected package
langroid
Fixed in
0.59.32
Disclosed
2026

Summary

Affected Scope langroid <= 0.59.31 Vulnerability Description CVE-2025-46724 fix bypass: TableChatAgent can call pandaseval tool to evaluate the expression. There is a WAF in langroid/utils/pandasutils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to literalok() 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. Reproduction & PoC This payload is used to bypass the waf, when executed, the column name import('os').system('ls')#... will be passed to eval here is the PoC Note: This test runs in a fully controlled environment. """ Run the chat response = task.run(prompt) print(response) ` after running this poc, command ls will be executed on the server <img width="2501" height="1256" alt="image" src="https://github.com/user-attachments/assets/98b83585-68e0-4be4-a7a6-21909fed662e" /> Gadget pandaseval (langroid\agent\special\tablechatagent.py:239) handletoolmessage (langroid\agent\base.py:2092) handlemessage (langroid\agent\base.py:1744) agentresponse (langroid\agent\base.py:760) response (langroid\agent\task.py:1584) step (langroid\agent\task.py:1261) run (langroid\agent\task.py:827) Security Impact Remote Code Execution (RCE) via pandaseval` tool. Attackers can execute arbitrary shell commands through controlled user input.

Impact

What is code injection?

Untrusted input is evaluated as executable code within the application's runtime environment. Typical impact: arbitrary code execution within the application's privilege context.

Affected versions

pip

  • langroid (<= 0.59.31)

Security releases

  • langroid → 0.59.32 (pip)
Kodem intelligence

Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.

Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter instead of chasing every advisory.

Kodem's Application Detection and Response identifies whether CVE-2026-25481 is reachable in your applications. Explore runtime application protection for your team.

See if CVE-2026-25481 is reachable in your applications. Get a demo

Already deployed Kodem? See CVE-2026-25481 in your environment

Remediation advice

Upgrade langroid to 0.59.32 or later to resolve this vulnerability.

Kodem Kai can prioritize this vulnerability in your dependency tree and generate a fix recommendation.

Frequently asked questions about CVE-2026-25481

What is CVE-2026-25481?

CVE-2026-25481 is a critical-severity code injection vulnerability in langroid (pip), affecting versions <= 0.59.31. It is fixed in 0.59.32. Untrusted input is evaluated as executable code within the application's runtime environment.

Which versions of langroid are affected by CVE-2026-25481?

langroid (pip) versions <= 0.59.31 is affected.

Is there a fix for CVE-2026-25481?

Yes. CVE-2026-25481 is fixed in 0.59.32. Upgrade to this version or later.

Is CVE-2026-25481 exploitable, and should I be worried?

Whether CVE-2026-25481 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo

What actually determines whether CVE-2026-25481 is exploitable, and how bad it is?

Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.

How do I fix CVE-2026-25481?

Upgrade langroid to 0.59.32 or later.

Stop the waste.
Protect your environment with Kodem.