tao-train-mask-auto-label

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow for tao-train-mask-auto-label ingests COCO annotation/image text from user-provided dataset archives (e.g., dataset.train_ann_path/dataset.val_ann_path → annotations.json) when constructing and running the mal train/evaluate/inference config, so an outsider can supply poison via the dataset inputs.