ai-music-generation

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions hosted on the inference-sh GitHub repository and provides commands to install related platform skills using npx. These resources are official components of the mentioned service platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it processes user-defined text prompts and lyrics to generate music.
  • Ingestion points: User-provided strings in the prompt and lyrics fields of the JSON input passed to the belt app run command in SKILL.md.
  • Boundary markers: The skill uses JSON structured input, providing basic delimitation between data and instructions.
  • Capability inventory: Employs the Bash tool, specifically restricted to the belt CLI tool for interacting with the inference API.
  • Sanitization: There is no evidence of explicit input filtering or sanitization within the provided markdown instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:13 PM
Security Audit — agent-trust-hub — ai-music-generation