inbox-triage
Warn
Audited by Snyk on Aug 20, 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). This skill’s runtime step “Fetch GitHub notifications” runs
gh api /notificationsand parses notification fields (reason,subject.title, etc.) from the outsider-authored inbox content (comments/replies/mentions/security alerts on third-party repos) without first selecting a specific known item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata