Skills
Navigate
skills/inference-sh/skills/ai-music-generation/Gen Agent Trust Hub

ai-music-generation

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to install the belt CLI via npx skills add belt-sh/cli and references installation documentation hosted on the inference-sh GitHub repository.
  • [COMMAND_EXECUTION]: The skill uses the belt command-line tool to interface with remote inference models. The execution scope is restricted to the belt toolset via the allowed-tools frontmatter configuration.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it processes untrusted data (prompts and lyrics) and interpolates them into tool commands.
  • Ingestion points: Prompt and lyric strings are ingested via the --input flag in the belt app run command examples within SKILL.md.
  • Boundary markers: The skill uses JSON structures to encapsulate user input, providing a basic structural boundary.
  • Capability inventory: The skill is authorized to execute the belt CLI tool.
  • Sanitization: No specific sanitization or filtering logic is defined for the input strings provided to the generation apps.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:32 PM
Security Audit — agent-trust-hub — ai-music-generation