zenml-pipeline-authoring

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to ingest and act on external, potentially untrusted data sources (e.g., "Injecting External Data" / Pattern D and references/external-data.md show reading arbitrary API endpoints with requests.get(endpoint) and registering/reading data from cloud URIs like s3://...), and those inputs are used to drive pipeline logic and dynamic DAG decisions, so third-party content can materially influence behavior.