ai-music-generation

Warn

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install external dependencies using npx skills add belt-sh/cli and various skills from the inference-sh/skills repository. These packages are hosted on external registries and GitHub repositories that are not on the trusted vendor list.
  • [COMMAND_EXECUTION]: The skill requires the Bash tool to execute the belt CLI binary. While restricted to the belt command via the allowed-tools frontmatter, it enables the execution of an external binary that interacts with remote services.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-provided prompts and lyrics into JSON payloads for the belt command.
  • Ingestion points: User-provided strings for the --input argument in belt app run commands (e.g., prompts for music styles or song lyrics).
  • Boundary markers: None. The skill does not provide delimiters or instructions for the agent to ignore potentially malicious instructions embedded in the input strings.
  • Capability inventory: Execution of the belt CLI via Bash(belt *), allowing the agent to perform network-based music generation tasks.
  • Sanitization: No input sanitization or validation logic is visible in the skill instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — ai-music-generation