naval-perspective

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

• Third-party content exposure detected (high risk: 0.90). Yes — the skill's required workflow (Step 2 "Naval式研究") mandates using tools like "WebSearch等" to fetch and ingest public web sources (see "⚠️ 必须使用工具（WebSearch等）获取真实信息" in SKILL.md and the included references/ list of public URLs), so the agent will read untrusted third‑party content that can materially influence its actions.