openai-privacy-filter
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches model weights and configuration files from HuggingFace's official repository.
- [COMMAND_EXECUTION]: Installs and executes a local command-line tool (
opf) for text redaction, file processing, and model training. - [DATA_EXFILTRATION]: Accesses files and text inputs specifically to identify and mask sensitive data; the skill operates locally and does not transmit information to unauthorized external servers.
Audit Metadata