blog-geo

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent in "Step 1: Read Content" to extract full text, headings, schema and robots.txt from blog posts (i.e., public/published URLs) and optionally query GSC for a published URL, meaning it ingests untrusted third‑party web content that directly influences scoring and recommended actions.