CVE-2026-54769
langroid langroid 취약점
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 `gl...
- 대응 우선순위
- 점검
- CVSS
- 10
- EPSS
- 0.64% 백분위 46.9% · 2026.07.28 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.07.10