Knowledge Graph Builder

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly lists "Unstructured: Documents, web content, text files" as data sources and includes LLM-based extraction (e.g., the extract_with_llm function and document ingestion pipelines) that read and interpret that content, so it ingests untrusted public web/user-generated content as part of its workflow.