seo-optimize

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

• Third-party content exposure detected (high risk: 0.90). Yes — SKILL.md explicitly instructs the agent to parse a user-provided Published URL (Step 1: on_page_content_parsing) and to call public web/search-data tools (Steps 3–5: dataforseo_labs_google_ranked_keywords, content_analysis_search, ai_opt_llm_ment_search), which ingest untrusted public web pages and search results that the agent reads and uses to drive verification, ranking checks, and recommendations.