check-pr
Warn
Audited by Snyk on May 5, 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). Yes — SKILL.md explicitly instructs the agent to fetch and read public, user-generated GitHub content (e.g., gh api repos/docker/docs/pulls/$ARGUMENTS/comments to get comment bodies, gh pr view --json reviews/comments and the lastComment.body, and follow CI detailsUrl), and that content is read and acted on (fixes, replies, resolving threads), which could enable indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata