music
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes music prompts provided by users or external sources, which creates a surface for indirect prompt injection.
- Ingestion points:
SKILL.mdandreferences/api_reference.md(viapromptparameter inmusic.composeandmusic.composition_plan.create). - Boundary markers: Absent; user-provided prompts are passed directly to the API without delimiters or instructions to ignore embedded commands.
- Capability inventory: Network access to ElevenLabs API and local file system access for writing audio files (
output.mp3). - Sanitization: Absent at the skill level; the skill relies on ElevenLabs' server-side safety filters to block copyrighted or harmful content.
- [EXTERNAL_DOWNLOADS]: The skill depends on official external libraries for interaction with the ElevenLabs service.
- Python:
elevenlabspackage from PyPI. - Node.js:
@elevenlabs/elevenlabs-jspackage from NPM. - These are the official SDKs provided by ElevenLabs.
Audit Metadata