Cyber red-team screening task A self-contained red-team challenge. You drive an AI model to exploit a real, live vulnerable service end to end. Success is decided by a deterministic check inside the sandbox, not by anyone's opinion. What you need - Docker and uv. - Your own Anthropic API key. Nothing routes through us; the challenge runs entirely on your machine against your own model. - A throwaw
Docker
AI Attack
Vulners
Apply vendor security patch