openai-whisper-api

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/transcribe.sh executes the curl command to interact with the OpenAI API. It uses standard bash argument parsing and employs double-quoting for variables to prevent basic shell injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: The script initiates network connections to api.openai.com. This is the official and well-known domain for OpenAI's API services, which is consistent with the skill's stated purpose of audio transcription.
  • [CREDENTIALS_UNSAFE]: The skill requires an OPENAI_API_KEY environment variable. The script correctly checks for its presence before attempting to execute the transcription request. This is the standard method for authenticating with this service.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 06:54 AM