elevenlabs-voice-changer

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow (“belt app run elevenlabs/voice-changer --input '{ "audio": "https://...mp3", ... }'”) fetches outsider-authored free-form content from an arbitrary external URL (public web audio) that the CLI reads/ingests as audio for processing.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes remote apps via the inference.sh CLI (e.g., "belt app run elevenlabs/voice-changer"), which at runtime runs code hosted by https://inference.sh, so remote content is executed and required for the skill to operate.