ai-music-generation
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions and additional skills located at the inference-sh GitHub repository. These downloads are associated with the official platform's tooling.
- [COMMAND_EXECUTION]: The skill uses the belt CLI tool to run AI models for music generation, including commands such as belt app run and belt app list.
- [PROMPT_INJECTION]: The skill accepts user-provided text for music prompts and lyrics. This constitutes an indirect prompt injection surface as these inputs are passed to the underlying AI models.
- Ingestion points: prompt and lyrics fields defined in SKILL.md.
- Boundary markers: User inputs are encapsulated within JSON strings passed to the CLI tool.
- Capability inventory: The skill utilizes subprocess execution via the belt command to interact with music models.
- Sanitization: The instructions do not define explicit sanitization or filtering for the music prompts.
Audit Metadata