elevenlabs-voice-isolator
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the ElevenLabs CLI and SDKs from official sources including npm, PyPI, and GitHub. These are standard packages provided by the service for API integration.
- [REMOTE_CODE_EXECUTION]: The installation documentation references a shell script installer from the official ElevenLabs GitHub repository (
curl ... | sh). This is a common installation pattern for CLI tools and originates from the service provider's verified infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external audio data from local files or remote URLs, which constitutes an ingestion point for untrusted data.
- Ingestion points: Local audio files and remote content fetched via
requests.get()inSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded content are provided for the audio data.
- Capability inventory: The skill possesses network access (calling the ElevenLabs API) and file system access (writing the isolated audio output).
- Sanitization: There is no sanitization of the input audio content, as the skill's primary function is to perform digital signal processing (voice isolation) on the provided bitstream.
Audit Metadata