elevenlabs-music
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external tools and dependencies from the 'inference-sh' GitHub organization and the 'inference.sh' domain. These resources are provided by the skill vendor for its core functionality.
- [COMMAND_EXECUTION]: The skill uses the 'belt' CLI tool via Bash to interact with the ElevenLabs music generation API. Access is restricted to the 'belt' command in the frontmatter.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text strings which are passed to an external AI model, creating a surface for potential indirect prompt injection.
- Ingestion points: The 'prompt' and 'duration_seconds' parameters used in the 'belt app run elevenlabs/music' examples.
- Boundary markers: Input parameters are structured within a JSON object passed to the CLI tool.
- Capability inventory: Execution of the 'belt' CLI tool for audio processing and remote API interaction.
- Sanitization: The skill definition does not specify any sanitization, filtering, or validation for the user-provided prompt content.
Audit Metadata