hunt-llm-ai

SUSPICIOUS/HIGH-RISK skill. It is internally consistent as an AI security testing playbook, but its actual footprint is an offensive exploitation guide for AI agents: prompt/system extraction, OOB exfil validation, SSRF via tool use, cloud metadata targeting, and covert payloads. There is little installer risk, but the operational risk is high because it equips the agent to perform real attack techniques and use known exfiltration endpoints.