seo-audit

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly directs the agent to fetch and render arbitrary public websites and related files (via web_fetch/curl and a browser rendering tool) and to inspect robots.txt, sitemaps, and pages (see the "Schema Markup Detection Limitation" and "Tools Referenced" sections), so untrusted third‑party page content is read and used to drive audit decisions.