review-pr
Warn
Audited by Socket on Aug 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's GitHub review capabilities broadly match its stated PR-review purpose, but it combines autonomous public posting under the user's identity, hidden automation markers/no AI disclosure, transitive sub-skill/plugin execution, and processing of untrusted PR content with write access. No direct credential theft or off-platform exfiltration is shown, so this is not confirmed malware, but it is a high-risk review automation skill.
Confidence: 89%Severity: 76%
Audit Metadata