seo-content

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

• Third-party content exposure detected (high risk: 0.85). The skill’s workflow is an E-E-A-T/content-quality analysis that (per its examples) performs a runtime WebFetch of a user-supplied URL and then feeds the fetched page text into the agent’s LLM context, which is outsider-authored public web content (public web pages/articles scraped at runtime).