OpenAI Whisper API
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to OpenAI's official API endpoint (
https://api.openai.com/v1/audio/transcriptions) to provide transcription services. As a well-known and trusted service provider, this connection is documented neutrally. - [COMMAND_EXECUTION]: Uses
curlto perform network operations andmkdirto prepare directories for output files. The script uses standard shell quoting for variables to prevent basic command injection. - [DATA_EXFILTRATION]: Transmits audio files to OpenAI for processing. This is the intended behavior of the skill and targets a trusted domain, representing no unauthorized data exposure.
- [PROMPT_INJECTION]: The skill provides an interface for the Whisper API's prompt feature. Ingestion points:
scripts/transcribe.shvia the--promptargument and the audio file input. Boundary markers: None. Capability inventory: Usescurlfor networking and redirection for file writing. Sanitization: Relies on standard shell variable quoting.
Audit Metadata