elevenlabs-voice-changer
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external installation instructions for the required CLI tool, hosted on GitHub (inference-sh/skills). It also provides instructions to install the 'belt-sh/cli' component using the npx package runner.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process audio files retrieved from external URLs provided in JSON inputs, creating a surface for potential indirect prompt injection attacks where malicious instructions could be embedded in the processed data. * Ingestion points: Input JSON fields such as 'audio' in SKILL.md examples. * Boundary markers: None identified to isolate or ignore instructions within the processed audio content. * Capability inventory: The skill uses the Bash tool to execute the 'belt' CLI for audio transformation. * Sanitization: The documentation does not specify any validation or sanitization protocols for external audio sources.
Audit Metadata