AI Leaked the API Key. Red Team Used It. | Prompt to Prod - with Michael Kouremetis
A red team was ready for a week of reverse engineering. The model handed them the API key instead — it was sitting in the training data.
Michael Kouremetis builds offensive cyber agents and evaluations on the Capabilities Team at Dreadnode, including DreadIndex, a living benchmark of how well models actually perform offensive security tasks. We get into why public benchmark scores didn't match what his team saw day to day, how models went from unreliable tool calling to "just give it a bash tool" in a year, and why his research has moved from "can it do this?" to scope and control. Plus…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.