Security

Note

Index content is sent to the embedding and LLM APIs. Choose providers and models with regard to data protection (e.g. processing in the EU, privacy policy).
Use Caching (aiCacheLifetime) and optional rate limiting to reduce cost and load.

RAG context and prompt injection

The retrieved index content (title, abstract, content) is passed as context to the LLM. Only index trusted content. If the index contains manipulated or untrusted text (e.g. instructions like “Ignore previous instructions…”), the model may follow them and alter the answer. Treat indexed content as part of the trusted prompt; avoid indexing user-generated or unmoderated content if you cannot accept this risk.

System prompt event

When using ModifyAiGeneratedSystemPromptEvent, do not inject user-controlled or unfiltered input into the system prompt. The system prompt should remain under your control; listeners must only add static or sanitized instructions so that the prompt stays trusted.