finding-data-lake-assets

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

• Third-party content exposure detected (high risk: 0.75). This workflow can ingest customer-authored Glue Discovery catalog fields (Description, Forms, embedded JSON from get-asset/batch-get-iterable-forms) into the agent context, since it explicitly retrieves and uses those untrusted text/metadata at runtime.