elevenlabs-voice-isolator
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external resources for installation and configuration, specifically pointing to an official GitHub repository for CLI installation guidelines and recommending the installation of the belt-sh/cli tool. These resources are provided by the service platform.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external audio content via URLs, which represents a potential ingestion point for untrusted data. * Ingestion points: The input JSON object in shell command examples accepts external URLs for audio files. * Boundary markers: The skill does not provide specific instructions or markers to delimit external content or ignore potential embedded instructions. * Capability inventory: The skill utilizes the belt CLI tool to process remote audio data. * Sanitization: No explicit validation or sanitization of input URLs or the data they point to is mentioned in the documentation.
Audit Metadata