on-page-seo-auditor

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and reads arbitrary public page content (user-supplied URLs) — see SKILL.md "Data Sources" and the "Instructions" Step 1 which require reading a page's H1/title/meta and inferring keywords — and those fetched pages are used to drive scores, recommendations, and next actions, so untrusted third‑party content could materially influence behavior.