red-teaming

SUSPICIOUS: the skill is internally consistent as a red-teaming methodology, but its stated purpose is inherently to equip an AI agent with offensive security capabilities, stealth tactics, and attack-planning patterns. There are no direct credential-harvesting, installer, or exfiltration behaviors in the provided file, so this is not confirmed malware; however, it is a high-risk offensive-security skill that could be misused and should not be treated as benign.