code-reviewers
Warn
Audited by Snyk on Aug 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow has reviewers “Inspect the diff carefully” and then communicate via
SendMessage, meaning the LLM ingests the repository diff/content that is user-controlled rather than trusted first-party provider text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata