AI SECURITY • 350 / 397
Understand how untrusted text, tools and autonomy create new attack paths.
RAG Poisoning
RAG poisoning inserts malicious or misleading content into a knowledge base so retrieval feeds harmful context to the model.
Think of it like
Think of RAG Poisoning as an input-trust or privilege problem: words can influence software decisions, so boundaries must be explicit.
Real life
Email, documents and web pages can become hostile inputs to AI systems through attacks involving RAG Poisoning.
SRE lens
A fake runbook can cause wrong production recommendations.
Remember thisRAG poisoning inserts malicious or misleading content into a knowledge base so retrieval feeds harmful context to the model.