hot-topics

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches user-generated trending posts and topic titles from public social platforms (Weibo, Zhihu, Baidu, Douyin, Toutiao, Bilibili) via the external API endpoints at https://60s.viki.moe/v2, and the agent directly reads and processes that untrusted third-party content in its workflows.