review-pr
Warn
Audited by Socket on Mar 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill is purpose-aligned for automated GitHub PR review, and its data flows stay on official GitHub tooling/endpoints. However, it grants the agent high-impact autonomous repository actions—including approvals, comments, CI reruns, issue edits, thread resolution, and optional direct pushes—while consuming untrusted PR content, making it a high-risk automation skill despite lacking obvious malware or credential-harvesting behavior.
Confidence: 91%Severity: 74%
Audit Metadata