tao-train-depth-anything-v2

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow ingests outsider-authored free text via the user-provided per-line annotation file (data_sources[*].data_file → annotations.txt), which is parsed as text inside the container by the depth_net train/evaluate/inference/quantize actions; this file content is not authored by the operating user and can contain arbitrary strings.