ai-music-generation

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external installation documentation and configuration files located in the inference-sh GitHub repository.- [REMOTE_CODE_EXECUTION]: Instructions direct users to install external CLI utilities and platform-specific skills using the npx package runner.- [COMMAND_EXECUTION]: Uses the belt CLI tool to run remote inference applications such as Diffrythm and Tencent Song Generation.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied text prompts and lyrics which are processed by remote AI models.
  • Ingestion points: User prompts and lyrics are passed via the --input parameter in the belt app run command found in SKILL.md.
  • Boundary markers: The skill uses JSON formatting to structure inputs, providing a data-to-command boundary.
  • Capability inventory: The skill execution environment is restricted to the belt CLI tool through the Bash(belt *) configuration in the frontmatter.
  • Sanitization: The instructions do not specify explicit sanitization or filtering of the user-provided prompt strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — ai-music-generation