create-music-elevenlabs

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/gen_music.py invokes ffmpeg via subprocess.run to normalize audio levels and apply fades to the generated music. The command arguments are passed as a list to avoid shell parsing risks.
  • [CREDENTIALS_UNSAFE]: The skill accesses ~/.gooseworks/credentials.json to retrieve the API key and base URL required for proxy authentication. This behavior is consistent with the vendor's (gooseworks-ai) infrastructure for usage tracking.
  • [EXTERNAL_DOWNLOADS]: Requests are sent to a GooseWorks internal proxy at a URL defined in the user's credentials file. This allows the skill to interface with ElevenLabs Music services while billing usage to the agent.
  • [PROMPT_INJECTION]: The skill processes user-supplied music prompts via the --prompt argument in scripts/gen_music.py. The data is passed to the generation API as untrusted input without specific delimiters or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 09:42 AM
Security Audit — agent-trust-hub — create-music-elevenlabs