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.
Published: 2026-07-09
Score: 10 Critical
EPSS: n/a
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Analysis and contextual insights are available on OpenCVE Cloud.

Remediation

No vendor fix or workaround currently provided.

Additional remediation guidance may be available on OpenCVE Cloud.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-q9p7-wqxg-mrhc Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent
History

Fri, 10 Jul 2026 00:15:00 +0000

Type Values Removed Values Added
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.
Title Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent
Weaknesses CWE-94
References
Metrics cvssV3_1

{'score': 10, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H'}

Subscriptions

No data.

cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-07-09T23:51:10.855Z

Reserved: 2026-06-15T23:23:57.713Z

Link: CVE-2026-54769

cve-icon Vulnrichment

No data.

cve-icon NVD

No data.

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses