safe-publish
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs using WebFetch to check the published URL and to verify that the live site returns content (Site Accessibility Check / Post-Publish Verification), which causes the agent to fetch and interpret arbitrary public website content (untrusted third‑party/user-generated), exposing it to indirect prompt injection risk.
Audit Metadata