CVE-2026-54769
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.
No public exploitation has been reported so far. No distribution fix is listed yet; apply vendor mitigations and monitor.
Recommended action: Track your distribution's security tracker and apply the fix as soon as it ships.
Severity metrics
CVSS 3.1 : 10.0 CRITICAL
Vector: AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Affected & fixed versions by distribution
Versions are the native distribution strings (backport-aware): RHEL/Debian/SUSE backport fixes, so compare with the distro version comparator (dpkg / rpm / vercmp), not the upstream version.
No affected package in the tracked watchlist yet (Debian, Ubuntu, Arch, SUSE, Red Hat...). Triage may still be pending.