engineering-elevenlabs-sound-music
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill interacts with the ElevenLabs API and Google Vertex AI (Lyria) for generating audio assets. These are well-known and reputable services for AI-driven content generation, and the skill follows standard integration patterns using their official endpoints and libraries.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of natural language prompts to drive audio generation models. This surface is fundamental to the skill's primary purpose and relies on the safety guardrails of the remote AI providers.
- Ingestion points: Prompts are passed to generation methods in
boilerplate/elevenlabs-client.ts,boilerplate/elevenlabs-music-client.ts, andboilerplate/lyria-client.ts. - Boundary markers: None provided in the templates to separate user prompts from internal system instructions.
- Capability inventory: The skill performs network requests to AI providers and writes the resulting audio data to the local file system using
Bun.writeandfs.writeFile. - Sanitization: No explicit sanitization of prompts is performed before they are sent to the external providers.
Audit Metadata