text-to-speech

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill instructs the user to install official packages elevenlabs (Python) and @elevenlabs/elevenlabs-js (JS). These are standard dependencies for the service provided.
  • [DATA_EXFILTRATION] (SAFE): Network communication is limited to the official ElevenLabs API endpoint (api.elevenlabs.io). Sensitive data like the ELEVENLABS_API_KEY is handled through environment variables, which is a recommended security practice.
  • [COMMAND_EXECUTION] (SAFE): The references/streaming.md file contains a Python example using subprocess.Popen to call ffplay. This is a legitimate use case for playing streaming audio data, and the command arguments are hardcoded and safe.
  • [PROMPT_INJECTION] (SAFE): No prompt injection patterns or attempts to override agent behavior were detected in the documentation or code snippets.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill processes user-provided text for speech generation, it does not execute this text as logic or feed it back into an agent's decision-making flow in a way that introduces risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 04:25 PM