ml-pipeline-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill's DAGs and Kubeflow pipelines explicitly load and validate data from external sources such as s3://my-bucket/data/train.csv and /data/.csv and connect to external MLflow/Kubeflow endpoints (e.g., http://mlflow.example.com, http://kubeflow.example.com) whose untrusted/user-provided content is read and used to drive training, branching, and deployment decisions (see SKILL.md and references/ examples).