openai-whisper-api
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill interacts with OpenAI's official API endpoint to perform audio transcriptions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external audio data which could contain instructions intended to influence the agent once the transcription is read.
- Ingestion points: The audio file path provided to the transcription script.
- Boundary markers: Output is written directly to a file without specific boundary delimiters.
- Capability inventory: Performs network requests to OpenAI and local file system writes.
- Sanitization: No content validation or sanitization is performed on the transcription output.
Audit Metadata