openai-whisper-api

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a bash script (scripts/transcribe.sh) to execute curl commands. This is the intended functionality to interact with the OpenAI API and is performed using standard shell practices.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with https://api.openai.com. As this is a well-known service and the primary endpoint for the skill's stated purpose, this network operation is considered safe.
  • [DATA_EXFILTRATION]: The skill sends the user-provided audio file and the OPENAI_API_KEY environment variable to OpenAI. This is necessary for the transcription service to function and is consistent with the skill's description. No data is sent to unexpected or untrusted destinations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:07 AM