attack-surface-recon

This skill is coherent with its stated purpose, but that purpose is high-risk: it equips an AI agent to perform offensive reconnaissance, active scanning, and vulnerability discovery against targets. There is no clear credential harvesting or hidden exfiltration, and the lone flagged pattern is a benign parse step rather than code execution. The main risk comes from granting an agent structured offensive security capability and broad network action, not from malware-like behavior.