elevenlabs-music-generation

Pass

Audited by Gen Agent Trust Hub on May 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the runcomfy CLI to execute music generation tasks. The allowed-tools frontmatter correctly limits the Bash tool to only execute commands prefixed with runcomfy, which follows the principle of least privilege.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install the @runcomfy/cli package from NPM. This is a standard method for installing developer tools from a public registry.
  • [CREDENTIALS_UNSAFE]: The skill references local storage of API tokens in ~/.config/runcomfy/token.json. It explicitly advises users on secure handling, such as setting file permissions to 0600 and avoiding logging the token, which aligns with security best practices for CLI tools.
  • [PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety guidelines was found. The skill's instructions focus entirely on the operational parameters for music generation.
  • [DATA_EXFILTRATION]: While the skill transmits user-provided prompts and lyrics to runcomfy.net, this is the intended functionality of the service. The documentation explicitly lists the allowed outbound endpoints, providing transparency into its network operations.
Audit Metadata
Risk Level
SAFE
Analyzed
May 27, 2026, 11:00 AM
Security Audit — agent-trust-hub — elevenlabs-music-generation