tooluniverse-diagnostic-test-evaluation

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow for Step 2 ingests an outsider-provided CSV file (python ... --input scores.csv), whose contents (labels/scores) are free-form text from outside the operating user and are read into LLM context via the tool’s printed ROC text (AUC/CI/cutoff/curve).