sound-effects
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes official ElevenLabs SDKs, specifically the 'elevenlabs' Python package and the '@elevenlabs/elevenlabs-js' npm package, downloaded from standard registries.
- [DATA_EXPOSURE]: The skill manages authentication using the ELEVENLABS_API_KEY environment variable. All network requests are directed to the official ElevenLabs API endpoint (api.elevenlabs.io).
- [INDIRECT_PROMPT_INJECTION]: The skill accepts text input for sound generation, which is a common ingestion point for external data. However, the risk is minimal as the input is used exclusively for audio generation by a specialized model.
- Ingestion points: The 'text' parameter in the SDK conversion methods.
- Boundary markers: None present in the provided examples.
- Capability inventory: Performs network POST requests to the ElevenLabs API and writes audio files to the local file system (e.g., 'thunder.mp3').
- Sanitization: No explicit sanitization or filtering is applied to the input text before transmission.
Audit Metadata