shuzishengmingkazike-skill

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires "每天搜集全网AI资讯，然后用AI模型帮助打分、筛选，挑出最重要的10条发到30多个社群" and similar steps ("先搜集全网资讯，再选10条"), which shows the agent is expected to fetch and interpret open/public (potentially user-generated) web/social content and act on it, allowing untrusted third-party content to influence decisions.