content-scaling

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md Step 1.1 ("灵感来源清单") explicitly instructs collecting and using competitor posts, comment sections, 热搜话题 and 小红书收藏 (public/user-generated social content) as inputs for topic selection and AI-assisted content generation, meaning the agent is expected to read and act on untrusted third‑party content.