google-news-seo

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly fetches and ingests live public webpages (Phase 1: "Use web_fetch to retrieve the page" under Schema Fetch Protocol and EEAT Step 2: "Use WebFetch to fetch the page; extract full page HTML, JSON-LD, and visible text"), so it reads untrusted third-party article content that directly influences analysis and follow-up recommendations.