urlcheck

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). Yes — SKILL.md explicitly instructs the agent to run url_scanner_scan / url_scanner_scan_with_intent on arbitrary target URLs (external web pages) before navigation, meaning the skill fetches and analyzes untrusted third‑party web content that can directly influence the agent's next actions.