validate-pr
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.78). At runtime the skill uses
gh pr view --json .../gh api .../pulls/{id}/commentsto fetch PR comments and inline review-thread text from GitHub, then that free-form outsider-authored content is provided to the LLM for validation and classification (indirect prompt-injection risk).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata