Monitor vulnerabilities like this one. Sign up free to get alerted when software you use is affected.
10.0

CVE-2026-54769: Langroid TableChatAgent: Unauthenticated Remote Code Execution

GHSA-q9p7-wqxg-mrhc CVE-2026-54769 CVE-2026-54769 CVE-2026-54769
Summary

Langroid's TableChatAgent is vulnerable to a critical security flaw that allows attackers to execute unauthorized code on the host system. This means an attacker could potentially take control of the system or access sensitive data. To protect against this, update Langroid to the latest version, which should include a fix for this issue.

What to do
  • Update langroid to version 0.65.2.
Affected software
Ecosystem VendorProductAffected versions
pip – langroid <= 0.65.1
Fix: upgrade to 0.65.2
– langroid langroid < 0.65.2
Original title
Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent
Original description
Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` capabilities. When these agents evaluate LLM-generated tool messages with `full_eval=True`, they attempt to sandbox the execution by explicitly setting `locals` to an empty dictionary `{}` inside Python's `eval()` function. However, this relies on an incomplete understanding of Python's execution model. Because `__builtins__` is not explicitly scrubbed from the `globals` dictionary mapping, Python implicitly injects all built-ins during execution, granting full access to functions like `__import__('os').system()`. Since `TableChatAgent.pandas_eval()` executes external LLM outputs natively, this bypass permits any attacker providing prompt payload to achieve unauthenticated RCE on the host system. Version 0.65.2 patches the issue.
ghsa CVSS3.1 10.0
Vulnerability type
CWE-94 Code Injection
Published: 9 Jul 2026 · Updated: 20 Jul 2026 · First seen: 6 Jul 2026