pronounce-button

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script (generate-pronunciation.py) to interface with the ElevenLabs API. This is the primary function of the skill and uses standard argument parsing for terms, output paths, and voice settings.
  • [EXTERNAL_DOWNLOADS]: The Python script makes POST requests to the official ElevenLabs API (api.elevenlabs.io) to fetch audio data. This is a well-known service and the interaction is limited to the skill's intended purpose.
  • [CREDENTIALS_UNSAFE]: The skill correctly instructs the user to provide the ELEVENLABS_API_KEY via an environment variable and explicitly warns against hardcoding or committing the key.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided terms and filenames. While it interpolates these into command lines and markdown files, it employs a slugify function to sanitize filenames and uses standard JSON encoding for API payloads, which mitigates common injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 01:27 PM
Security Audit — agent-trust-hub — pronounce-button