protocol-reverse-engineering

SUSPICIOUS: the skill is internally consistent as a protocol reverse-engineering guide, but it equips an AI agent with high-risk offensive security capabilities including MITM interception, TLS bypass, packet replay, and fuzzing. There is no obvious credential harvesting or malicious exfiltration path, so this is not confirmed malware; the main issue is that a security/exploit-oriented skill gives an agent dangerous real-world network action capability.