transcribe
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
openaiPython package from the official Python Package Index (PyPI). - [DATA_EXFILTRATION]: Audio data is transmitted to the OpenAI API for transcription processing. OpenAI is recognized as a well-known and trusted service provider.
- [PROMPT_INJECTION]: The skill processes untrusted audio files which creates a surface for indirect prompt injection.
- Ingestion points:
scripts/transcribe_diarize.pyreads audio files and speaker references provided by the user. - Boundary markers: None identified in the prompt logic.
- Capability inventory:
scripts/transcribe_diarize.pyperforms file reads/writes and network requests to the OpenAI API. - Sanitization: Content within audio files is not sanitized, but the risk is low as the output is primarily saved to disk and not used to drive sensitive system operations.
Audit Metadata