pentest-recon-surface-analysis
Warn
Audited by Socket on Sep 24, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally consistent and not showing credential theft, covert exfiltration, or malicious installers, but it equips an AI agent for offensive security reconnaissance. The only scanner hit is a benign documentation command example; the main risk comes from the pentest capability itself, not hidden behavior.
Confidence: 92%Severity: 78%
Audit Metadata