yolo-training

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were identified. The provided instructions follow standard machine learning practices.\n- [COMMAND_EXECUTION]: The skill documents example bash commands for model training using the yolo CLI. These commands are transparent and intended for execution in a local development environment using project-specific configuration files.\n- [SAFE]: The skill implements a diagnostic loop reading training metrics from a local CSV file. Ingestion point: runs/detect/train/results.csv in SKILL.md. Boundary markers: None. Capability inventory: pandas.read_csv, yolo CLI. Sanitization: Column name stripping. This pattern is evaluated as safe as it processes local training metadata to provide feedback to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 02:51 AM
Security Audit — agent-trust-hub — yolo-training