writing-assistant

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md → content/methods/01-选题.md "先验调研") explicitly mandates searching and judging public social platforms (小红书/知乎/微信搜一搜) and using the quantity/quality of those user-generated search results to decide topic selection, so the agent would ingest untrusted third-party content that can directly change its decisions and next actions.