media-info

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

• Third-party content exposure detected (high risk: 0.80). The skill directly fetches and displays content from public third‑party APIs (e.g., https://60s.viki.moe/v2/lyric, /v2/ncm-rank, /v2/maoyan/realtime/movie), causing the agent to ingest and render untrusted open‑web content (lyrics, chart items, movie/tv text) as part of its workflow which could carry indirect prompt injections.