listenhub-tts

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts arbitrary content URLs (the contentUrl field and "用户提供 URL 作为内容来源" in the 模式选择逻辑 / flow-speech/episodes workflow) and ingests that third‑party web content for synthesis/AI polishing, so untrusted webpage content could influence processing.