sound-effects

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends the installation of the elevenlabs Python package and the @elevenlabs/elevenlabs-js Node.js package. These are official software development kits for ElevenLabs, a widely recognized service for audio generation.
  • [COMMAND_EXECUTION]: The instructions include cURL command examples for interacting with the ElevenLabs REST API. This is a standard practice for documenting API functionality and allows for verification of the service's features.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes user-provided descriptions to generate audio content.
  • Ingestion points: The text parameter in the conversion methods (SKILL.md) accepts arbitrary descriptive strings.
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent to isolate the user input from the rest of the operational prompt.
  • Capability inventory: The skill facilitates network requests to api.elevenlabs.io and writes the resulting binary audio data to local files (e.g., thunder.mp3).
  • Sanitization: The input text is passed directly to the generation model, which is common for non-executable audio generation tasks where the output is binary data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 06:31 PM