entertainment

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

• Third-party content exposure detected (high risk: 0.70). The skill fetches and displays arbitrary public content from the open API endpoints at https://60s.viki.moe/v2 (e.g., /hitokoto, /duanzi, /kfc, /luck), which are untrusted/third-party text sources that the agent reads and returns, allowing potential indirect prompt injection.