tao-train-depth-anything-v2
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches pretrained DINOv2 model weights from Meta's official public repository.
- [COMMAND_EXECUTION]: Outlines standard Docker commands for running model training, evaluation, and deployment using NVIDIA TAO containers.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied dataset annotation files during training and inference; however, it follows standard machine learning workflows and relies on platform-level agent guardrails.
Audit Metadata