Tag
Prompt injection
Attacks that hide instructions in the content an AI reads, and how they actually play out against real agents.
-
I tried six ways to make an AI agent leak recovery codes. One worked.
Four of six attacks never landed once, on any model. The one that worked reliably was the oldest con there is: authority, a reason to help, and a reason to stay quiet. It walked the recovery codes out the door in 9 of 10 runs on the cheapest model.