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 "web content" under Data Sources ("Unstructured: Documents, web content, text files") and shows LLM-based extraction that ingests arbitrary text (e.g., the extract_with_llm prompt that directly processes {text}), so it will fetch/ingest and interpret open/public third-party content which could contain injected instructions.