workflow-status
Warn
Audited by Snyk on Aug 22, 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’s required runtime workflow ingests outsider-authored text by running GitHub “forge” list commands (PR titles, labels, etc.) and may incorporate issue comment fallback via triage verdict text, so attacker-submitted content can be read and influence the produced envelope.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata