CyberAttack.ai

Red Teaming AI Agents: Prompt Injection, Poisoned RAG, and the Authorization Gap

5:29

AI agents have quietly become privilege brokers — taking model outputs, resolving them into tool calls, and executing against internal systems with service-account credentials that often carry sweeping permissions. This episode of CyberAttack.ai walks practitioners through the full red-team surface of production AI agents: the retrieval pipelines feeding them, the APIs they invoke, and the…