The Agent Skills Directory

[SAFE]: The skill's code and instructions align with its documented purpose and do not contain malicious patterns.
[COMMAND_EXECUTION]: Uses the standard curl utility to interact with the Groq API endpoint for audio processing.
[DATA_EXFILTRATION]: Sends user-provided audio files to api.groq.com for transcription. This is the intended behavior of the skill and targets a well-known, established service.
[CREDENTIALS_UNSAFE]: Provides secure instructions for API key management via environment variables or a local configuration file, correctly avoiding the use of hardcoded secrets.

transcribe