Langroid up to 0.65.1 TableChatAgent/VectorStore TableChatAgent.pandas_eval escape output

Summaryinfo

A vulnerability categorized as critical has been discovered in Langroid up to 0.65.1. Affected by this issue is the function TableChatAgent.pandas_eval of the component TableChatAgent/VectorStore. Such manipulation leads to escape output. This vulnerability is listed as CVE-2026-54769. The attack may be performed from remote. There is no available exploit.

Detailsinfo

A vulnerability was found in Langroid up to 0.65.1. It has been rated as critical. Affected by this issue is the function TableChatAgent.pandas_eval of the component TableChatAgent/VectorStore. The manipulation with an unknown input leads to a escape output vulnerability. Using CWE to declare the problem leads to CWE-116. The product prepares a structured message for communication with another component, but encoding or escaping of the data is either missing or done incorrectly. As a result, the intended structure of the message is not preserved. Impacted is confidentiality, integrity, and availability. CVE summarizes:

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.

The advisory is available at github.com. This vulnerability is handled as CVE-2026-54769 since 06/16/2026. The exploitation is known to be easy. The attack may be launched remotely. No form of authentication is required for exploitation. Technical details are known, but there is no available exploit.

Upgrading to version 0.65.2 eliminates this vulnerability.

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Productinfo

Name

• Langroid

Version

• 0.65.0
• 0.65.1

Website

• Product: https://github.com/langroid/langroid/

CPE 2.3info

• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion