The Agent Skills Directory

[SAFE]: The skill serves as a technical reference for using the Ultralytics YOLO library. It provides legitimate Python and CLI examples for model training, validation, and troubleshooting.
[CREDENTIALS_UNSAFE]: The skill demonstrates safe credential handling by instructing users to use environment variables with placeholders (YOUR_API_KEY) rather than hardcoding secrets.
[DATA_EXFILTRATION]: The skill references the vendor's own platform (ul:// URIs and ultralytics.com domains) for dataset management and metric streaming, which is the intended and transparent behavior of the tool.
[REMOTE_CODE_EXECUTION]: No suspicious remote script execution patterns (e.g., curl | bash) were detected. All code execution involves standard calls to the ultralytics library or CLI.

yolo-training