transcribe
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the official
openaiPython library from the standard Python Package Index (PyPI). This is a well-known and trusted dependency for interacting with OpenAI services. - [COMMAND_EXECUTION]: The skill uses a local Python script (
transcribe_diarize.py) to process audio files. The script is bundled with the skill and performs transcription by calling the OpenAI API via standard subprocess execution. - [DATA_EXFILTRATION]: Audio files are read locally and transmitted to OpenAI's API endpoints for processing. This behavior is consistent with the skill's stated purpose of transcription. There is no evidence of data being sent to unauthorized or suspicious third-party servers.
- [CREDENTIALS_UNSAFE]: The skill correctly identifies the need for an
OPENAI_API_KEYand explicitly instructs the agent not to ask the user to paste the key into the conversation, recommending instead that the user set it as a local environment variable.
Audit Metadata