openai-whisper-api
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bash script (
scripts/transcribe.sh) that usescurlto interact with an external API. The script uses double-quoting for variables to prevent common shell injection issues. - [DATA_EXFILTRATION]: Audio files are transmitted to OpenAI's official API endpoint for transcription. This is the intended purpose of the skill and involves a well-known service provider.
- [CREDENTIALS_UNSAFE]: The skill manages the OpenAI API key via an environment variable or a configuration file, which aligns with standard practices for secret management. No hardcoded credentials were found.
Audit Metadata