content-engine

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 Research explicitly instructs the agent to use web_search and analyze "top 5-10 ranking articles" and extract headings/angles from their public URLs (SKILL.md, "Competitor analysis: Use web_search to find the top 5-10 ranking articles for the target keyword"), which requires ingesting untrusted third‑party web content that directly guides research and drafting decisions.