AI RESEARCH
A Systematic Taxonomy of Security Vulnerabilities in the OpenClaw AI Agent Framework
arXiv CS.AI
•
ArXi:2603.27517v1 Announce Type: cross AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces--shell, filesystem, containers, and messaging-- Patch-differential evidence yields three principal findings. First, three Moderate- or High-severity advisories in the Gateway and Node-Host subsystems compose into a complete unauthenticated remote code execution (RCE) path--spanning delivery, exploitation, and command-and-control--from an LLM tool call to the host process.