mlops

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow shown in templates/kubeflow-pipeline.yaml runs an engineer-features step that executes inline Python (pd.read_parquet("{{inputs.parameters.data-path}}") and computes features), meaning outsider-authored text/data can enter via the pipeline parameter data-path without selecting a specific trusted item first.