fine-tuning-openvla-oft
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill documentation and workflows are dedicated to reproducing results from the OpenVLA-OFT research paper. All external repository references point to legitimate research or organizational GitHub accounts.
- [COMMAND_EXECUTION]: The skill includes shell commands for environment setup, training via torchrun, and deployment using FastAPI. These are essential for the primary purpose of the skill and follow standard development practices.
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to fetch the official repository, standard simulation environments, and model weights from trusted platforms like GitHub and Hugging Face. These downloads are required for the project and do not pose a risk.
Audit Metadata