eo-miniapp-ideation

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs using open/public social platforms (e.g., "去小红书/抖音搜核心关键词" and inspecting WeChat search/listings) to read and analyze user-generated content as part of the required validation workflow, so third-party content would be ingested and could influence decisions.