project-setup
Warn
Audited by Socket on Apr 28, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
BENIGN in purpose and data flow, but operationally high-impact: it autonomously performs real GitHub account/org actions using the user's existing credentials. No clear malware or exfiltration behavior is present, yet the subagent/autonomous repo administration design makes it a medium-high security risk skill.
Confidence: 91%Severity: 72%
Audit Metadata