ci-sentinel
Warn
Audited by Snyk on Aug 4, 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 describes a daily GitHub Actions cron that reads outsider-authored PR FAILURE check data and then runs
/ci-debug/claude -pon it for each PR (classifier reads CI logs and PR titles/bodies as untrusted input at runtime).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata