request-review
Warn
Audited by Socket on Mar 15, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's purpose is coherent with code-review orchestration, and its GitHub/review.log data flow is proportionate. The main concern is execution of an opaque home-directory wrapper whose provenance and behavior are not independently verifiable from the skill, creating a meaningful trust and supply-chain risk even without obvious exfiltration or credential harvesting.
Confidence: 82%Severity: 72%
Audit Metadata