gpt-review
Warn
Audited by Socket on Oct 19, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's review purpose is coherent, but it materially relies on a third-party orchestration layer and external CLI that handle repository content and auth context. The main concern is credential/data routing through Cloudroom rather than direct official OpenAI API use, combined with direct-binary install trust.
Confidence: 88%Severity: 76%
Audit Metadata