lpbf-defect-prediction
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads MeltpoolNet dataset files from the official BaratiLab GitHub repository to the user's local cache directory (~/.cache/mechanical-engineering-skills/meltpoolnet). These files are processed as numerical data for training classifiers.
- [COMMAND_EXECUTION]: The script provides a command-line interface for data augmentation, model training, and defect prediction using standard scientific computing packages such as numpy, pandas, and scikit-learn.
- [DYNAMIC_EXECUTION]: Uses
joblibfor model persistence. This allows the user to save trained model weights to a file and load them later for predictions. The workflow is designed for local model management.
Audit Metadata