munger-perspective

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

• Third-party content exposure detected (high risk: 1.00). The skill's required "Agentic Protocol" (SKILL.md Step 2: "⚠️ 必须使用工具（WebSearch等）获取真实信息，不可跳过") and the research index (references/research.md describing "5个并行Agent... 执行50+次WebSearch" and many public news/sites links) direct the agent to fetch and interpret open/public third‑party web content (CNBC, Bloomberg, blogs, etc.) which will materially inform its judgments and next actions, creating clear exposure to untrusted third‑party content that could enable indirect prompt injection.