Autonomous AI penetration testing benchmark: an honest AI security testing leaderboard of a local-first autonomous AI pentester across OWASP Juice Shop, cloud (AWS, Azure, GCP), infrastructure and IoTGoat labs. Every finding proven by exploit. Part of Darkmoon.
benchmark penetration-testing pentesting offensive-security iot-security owasp-juice-shop ai-agents vulnerability-scanner cloud-security security-testing redteam autonomous-ai ai-red-team llm-security ci-cd-security cloud-pentest ai-penetration-testing ai-security-benchmark ai-pentest-benchmark autonomous-pentest
-
Updated
Sep 30, 2026