elevenlabs-music

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation resources hosted on the inference-sh GitHub repository for setting up the belt CLI tool.- [COMMAND_EXECUTION]: It uses the belt CLI via shell commands to manage authentication and execute remote music generation and media merging applications.- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text for generating music prompts, which constitutes a potential injection surface.
  • Ingestion points: The prompt parameter in the belt app run CLI command.
  • Boundary markers: Input is encapsulated within a JSON structure passed to the CLI command line.
  • Capability inventory: The skill utilizes the Bash tool to execute commands that communicate with external AI services.
  • Sanitization: Input is treated as a string within the JSON payload; no specific filtering or sanitization of the prompt content is implemented.- [NO_CODE]: The skill primarily provides documentation and usage examples for external CLI tools and does not include custom scripts or executables.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:18 PM
Security Audit — agent-trust-hub — elevenlabs-music