shortvideo-knowledge-script

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

• Third-party content exposure detected (low risk: 0.10). The skill workflow guides the agent to search across the web or platforms (like Xiaohongshu, Zhihu, Baidu, competitor comments) for material, but requires the agent to actively search and filter sources rather than consuming an unselected external feed.