Read as
Last updated: April 29, 2026
RAG combines vector search + LLM. Security model is hybrid.
RAG combines vector search + LLM. Security model is hybrid.
Threats specific to RAG
- Vector store data exposure — anyone with access reads embeddings (and retrieves originals)
- Indirect prompt injection via retrieved docs — adversary plants malicious doc; RAG retrieves and follows instructions
- IAM bypass via vector similarity — user query semantically matches private docs they shouldn’t see
- Hallucinated citations — LLM cites nonexistent sources
Want this for your team?
Custom team training + practitioner advisory
Beyond the free academy — we run private workshops, vCISO advisory, and red-team exercises tailored to your stack. For Indian SMBs scaling past their first hire.
Book team training call
Replies in 4 working hrs · India-only · Senior consultants