# The 0.1% Problem: How One in a Thousand Documents Can Hijack an AI Agent - Date: 2026-04-07 - Category: Artificial Intelligence Corrupting fewer than one in a thousand documents in a knowledge base is enough to hijack an AI agent that reads from it — DeepMind’s new taxonomy of agent attacks reveals six ways to compromise autonomous systems, and the most dangerous one requires almost no foothold at all. ---