pp-human-goat
Warn
Audited by Socket on Sep 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core capability matches the stated purpose, but the skill authorizes autonomous real-world hiring/canceling/calling with stored credentials and card-on-file, which is inherently high risk for an AI agent. Install trust is mixed: same-publisher sources exist, but they are third-party personal-org tooling with an unpinned Go fallback. The largest concern is not malware evidence but disproportionate autonomy plus an inconsistent 'read-only' claim despite clearly mutating actions.
Confidence: 91%Severity: 86%
Audit Metadata