skills/ultralytics/skills/yolo-models/Gen Agent Trust Hub

yolo-models

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation resource for Ultralytics YOLO models. The links provided (platform.ultralytics.com, docs.ultralytics.com) and the reference to Hugging Face for sam3.pt are official and well-known services.
  • [COMMAND_EXECUTION]: The skill provides a shell command to list known assets: python -c "from ultralytics.utils.downloads import GITHUB_ASSETS_NAMES; print(*sorted(GITHUB_ASSETS_NAMES), sep='\\n')". This is a benign informational command using the official ultralytics package.
  • [EXTERNAL_DOWNLOADS]: The documentation describes the behavior of the ultralytics library, which automatically downloads model weights from official GitHub release assets when a model is instantiated (e.g., YOLO("yolo26n.pt")). This is documented as standard library behavior. The mention of manually downloading sam3.pt from Hugging Face is also a standard procedure for gated models.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 03:02 PM
Security Audit — agent-trust-hub — yolo-models