aliyun-qwen-asr

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

• Third-party content exposure detected (high risk: 0.80). The skill's transcribe_audio.py and SKILL.md explicitly accept and fetch arbitrary public audio URLs (e.g., the --audio parameter and examples like "https://.../welcome.mp3") and return transcript text that an agent would read and act on, so untrusted third-party content can influence subsequent decisions.