open-webui-guide

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

• Third-party content exposure detected (high risk: 0.90). The skill's documentation shows Open WebUI ingesting and using external, potentially untrusted web content (e.g., RAG/Knowledge workflows in references/rag.md that add retrieved external documents into model context and pipeline/filter workflows in references/pipelines.md that call external HTTP services via OPENAI_API_BASE_URLS), so third‑party content can be fetched and materially influence model behavior.