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.
What this means
- Exposure
- Exploitable remotely over the network, without authentication and with no action from the victim.
- Impact
- An attacker can read sensitive data, modify or destroy data and take the service offline. The impact spreads beyond the vulnerable component into other parts of the system.
- Weakness
- The application interprets attacker-supplied code, which then runs with its privileges.
- Likelihood
- Its EPSS score stays low: nothing points to imminent exploitation, which is no reason to leave it unpatched.
What to doPatch without waiting for the next scheduled cycle. Start with the instances exposed to the internet.
Read automatically from the CVSS vector, the weakness type (CWE) and the EPSS score. The technical description above remains the one published by NIST.