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.
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| langroid | langroid | affected |
|
No data.
No data.
No data.
Project Subscriptions
No data.
Advisories
| Source | ID | Title |
|---|---|---|
 Github GHSA |
GHSA-q9p7-wqxg-mrhc | Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent |
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
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
|
Projects
Sign in to view the affected projects.
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
Vulnrichment
No data.
NVD
No data.
Redhat
No data.
OpenCVE Enrichment
No data.
Weaknesses