content-planner

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

• Third-party content exposure detected (high risk: 1.00). The skill's Phase 1 Research step explicitly performs "WebSearch 3-5 queries" and states "If input is URL → WebFetch phân tích nội dung" in SKILL.md Step 3 (and the header "Auto-researches via web search"), so the agent will fetch and interpret open/public third‑party web/URL content as part of its workflow which can materially influence planning and writing actions.