tao-train-depth-anything-v2

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow ingests outsider-authored free text via the user-provided per-line annotations.txt referenced by dataset.train_dataset.data_sources[*].data_file (and similarly val/test/infer), which the depth_net train CLI reads to construct the dataset; those annotation lines are arbitrary text from outside the operating user’s authorship.