tao-run-deft-aoi

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads training, validation, and testing dataset CSV files (e.g., train/base/training_set.csv, kpi/testing_set.csv) whose contents are user-provided free text ingested by the agent and data preparation scripts.