metatron-pentest-assistant

SUSPICIOUS. The skill's capabilities are internally consistent with a penetration-testing assistant, but it gives an AI agent offensive security functionality, including scanning, vulnerability analysis, and exploit-suggestion support, which is inherently high risk. Data flow is mostly local/official and not clearly exfiltrative, so this is not confirmed malware; the main concerns are offensive-agent enablement, personal-repo provenance, and medium supply-chain risk from download/execute installation steps.