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
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:57 PM