ci-first-verification
Warn
Audited by Snyk on Aug 17, 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). SKILL.md requires the agent to read CI results via GitHub CLI commands like
gh pr checks <number>/gh run view <run-id> --log-failed, which at runtime ingests outsider-authored PR logs/comments text from GitHub.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata