elevenlabs-music-generation

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the runcomfy CLI tool via the Bash tool to generate music and manage authentication.
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends installing the @runcomfy/cli Node.js package from the official npm registry to enable its functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input which could be used to influence the music generation process or agent behavior.
  • Ingestion points: The prompt field in the input JSON, which accepts user-provided style descriptions and lyrics.
  • Boundary markers: Content is encapsulated as a string within a JSON object passed to the CLI tool.
  • Capability inventory: The skill can execute the runcomfy CLI tool, which performs network operations to model-api.runcomfy.net and writes generated audio files to the local file system.
  • Sanitization: The documentation specifies that the CLI transmits the JSON body directly to the API without shell expansion, mitigating command injection risks at the CLI level, though the content is still interpreted by the generative model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:19 PM
Security Audit — agent-trust-hub — elevenlabs-music-generation