tao-train-depth-anything-v2
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration (references/skill_info.yaml) and instructions reference downloading pretrained model weights from Facebook Research's public file server (dl.fbaipublicfiles.com), a well-known and recognized source for AI research artifacts.
- [COMMAND_EXECUTION]: The skill provides detailed shell command templates for running model lifecycle actions within Docker containers. These instructions follow security best practices, such as using appropriate user and group ID mapping to ensure containerized processes do not run with unnecessary host-level privileges.
Audit Metadata