ai-music-generation

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a remote markdown file on GitHub (inference-sh/skills) to provide installation guidance for the required CLI tool.
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool to interact with AI music models. Execution is restricted to the belt command as defined in the allowed-tools configuration.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: User-provided text prompts are interpolated into CLI commands to generate music.
  • Boundary markers: Input is structured within JSON objects passed as arguments to the belt command.
  • Capability inventory: The skill is limited to executing the belt CLI for audio generation and model management.
  • Sanitization: Input is passed to the belt application which manages the interaction with the underlying inference models.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:54 PM
Security Audit — agent-trust-hub — ai-music-generation