review-pr
Warn
Audited by Snyk on Apr 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches PR content via "gh pr view" / "gh pr diff" (Phase 1 in SKILL.md) and injects the resulting CHANGED_FILES and file contents into agent prompts in Phase 3, so arbitrary user-generated PR text and code from GitHub can be read and used to drive decisions and actions (e.g., synthesized findings, TaskCreate, and
gh pr review)—creating a clear path for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata