What’s Vulnerable › Vulnerabilities

CVE-2026-54769: Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent

• Severity: critical (CVSS 10.0 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.9% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-07-10 · updated 2026-07-10
• Weakness: CWE-94

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.

Affected products

• langroid: before 0.65.2

References

• https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc
• https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc

Get alerted when CVE-2026-54769 or the next vulnerability affects your stack