AI RESEARCH
ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
arXiv CS.AI
•
ArXi:2603.15727v1 Announce Type: cross Autonomous LLM-based agents increasingly operate as long-running processes forming densely interconnected multi-agent ecosystems, whose security properties remain largely unexplored. In particular, OpenClaw, an open-source platform with over 40{,}000 active instances, has stood out recently with its persistent configurations, tool-execution privileges, and cross-platform messaging capabilities.