qwen-asr

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

• Third-party content exposure detected (low risk: 0.10). The workflow transcribes audio files to text via an ASR service, and audio content (voice messages) processed by ASR is considered untrusted outsider-authored speech/free text ingested by the agent.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The script connects to an arbitrary third-party Gradio demo backend (https://qwen-qwen3-asr-demo.ms.show) at runtime for execution, representing an unverifiable weak operational dependency.