google-news-seo

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

• Third-party content exposure detected (high risk: 1.00). Flagged because the SKILL.md workflow repeatedly requires fetching and interpreting arbitrary public web content (e.g., "Phase 1 — web_fetch" to retrieve page HTML/JSON-LD, "Step 1 — Simulate Google News index query" using WebSearch, and the Competitor Gap Analysis which instructs fetching competitor article URLs and News Sitemaps), and those untrusted third‑party pages are parsed and used to drive diagnostic routing and actions—so third‑party content can materially influence the agent's decisions.