story-long-write

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly instructs the agent to ingest and act on external, user-provided or searched materials (e.g., reading 对标/{书名}/原文/ and 对标/{书名}/拆文报告.md as reference, using /story-long-analyze to import originals, and spawning a story-researcher agent to "搜索并输出到 参考资料/"), so it will load untrusted public/user-generated content and use it to influence writing decisions.