elevenlabs-voice-changer
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references a GitHub URL to fetch CLI installation instructions from the platform's official repository and utilizes npx to add skills from the service provider's scopes. These are standard interactions with the platform's official resources and tools.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by processing audio content from external URLs provided as input to the belt CLI. Evidence chain: 1. Ingestion point: The 'audio' field in JSON inputs to the belt app run command; 2. Boundary markers: Data is structured within JSON objects; 3. Capability inventory: The skill uses the belt CLI tool via Bash; 4. Sanitization: Handled by the underlying platform tools. This is a standard functional requirement for processing remote media.
Audit Metadata