AI RESEARCH
Cochise: A Reference Harness for Autonomous Penetration Testing
arXiv CS.AI
•
ArXi:2605.11671v1 Announce Type: cross Recent work on LLM-driven autonomous penetration testing reports promising results, but existing systems often combine many architectural, prompting, and tool-integration choices, making it difficult to tell what is gained over a simple agent scaffold. We present cochise, a 597 LOC Python reference harness for autonomous penetration-testing experiments. Cochise connects an LLM-driven agent to a Linux execution host over SSH and s controlled target environments reachable from that jump host.