review-fix-codex
Warn
Audited by Socket on Apr 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated purpose is coherent, but the skill’s footprint is broader than necessary: it executes an unpinned third-party npm package as the primary control plane, grants broad `bunx` execution, and permits autonomous git/issue actions based on external review output. This looks more like a risky automation wrapper than overt malware.
Confidence: 83%Severity: 76%
Audit Metadata