I tried six ways to make an AI agent leak recovery codes. One worked.
I built a support agent and ran six attacks at it across three models. The technical tricks got nothing. The con that works on a tired help desk worked on the agent too.
I built a support agent and ran six attacks at it across three models. The technical tricks got nothing. The con that works on a tired help desk worked on the agent too.
AI lowered the barrier to building, not the bar a thing has to clear before real people and real data depend on it. Here's the gap, and what I'm doing about it.