content-content-creator

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md's core workflow ("选题来源框架") explicitly directs using open/public user-generated sources—e.g., 知乎热门, 百度知道/悟空问答, 评论区, 行业新闻和竞品文章—as topic/data sources the agent should consult and base content decisions on, which means untrusted third‑party content would be read and could influence actions.