pentest-ai-llm-security

SUSPICIOUS/HIGH-RISK skill. Its stated purpose is legitimate pentesting, and the named tools are generally from official sources, but the skill materially equips an AI agent to perform offensive security actions: prompt injection, system prompt extraction, data exfiltration testing, proxy interception, and excessive-agency abuse. That capability is coherent with a pentest skill, so this is not confirmed malware, but it is a high-risk security skill that should only be used with strict authorization and isolation.