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 `T...

Added to the CISA Known Exploited Vulnerabilities catalog on 10 Jul 2026. Vendor: AI/ML. Product: LLM. CVSS score: 10.

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 message...

Required action: Review and patch if applicable to your AI infrastructure.