vibe-pentest-ai-security-testing
Warn
Audited by Socket on Sep 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s behavior is broadly consistent with its stated purpose, but that purpose is an offensive security capability for AI agents: it captures live session credentials, drives automated vulnerability testing, and encourages active exploitation. No clear third-party credential exfiltration is shown, so this is not confirmed malware, but the combination of offensive use, session harvesting, and mutable install/update paths makes it high security risk.
Confidence: 85%Severity: 82%
Audit Metadata