code-review-assistant
Warn
Audited by Socket on Apr 2, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill is broadly aligned with PR review, but it is not low-risk. Its main issues are autonomous GitHub review actions, execution of unpinned external CLIs, and analysis of untrusted PR content with command/write capabilities. This is best classified as suspicious/high-vulnerability rather than confirmed malware.
Confidence: 84%Severity: 72%
Audit Metadata