transcript-polisher

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

• Third-party content exposure detected (high risk: 0.90). Flagged because the skill's required workflow (第四步：错字错词纠正) explicitly tells the agent "优先搜索确认" when unsure, which requires fetching/reading public web/search results to confirm transcribed terms and therefore lets untrusted third‑party content influence corrections and downstream actions.