create-generation-plugin

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow is to implement _generate() using self._retrieval_pipeline._retrieve_by_id(...) and self._service.get_chunk_contents(...), which at runtime will ingest retrieved chunk text originating from the configured retrieval pipeline’s stored documents (i.e., potentially outsider-authored content if the corpus includes non-user sources).