Michael Bargury

Rest assured, you're in the right place—I'll be posting content throughout Black Hat.

OpenAI recently released Agent mode. ChatGPT now wields a general purpose tool – its own web browser. It manipulates the mouse and keyboard directly. It can use any web tool, like we do. Any AI security researcher will tell you that this is 100x uptake on risk. Heck, even Sam Altman dedicated half his launch post warning that this is unsafe for sensitive use. Meanwhile AI guardrails are The leading idea in AI security. It’s safe to say they’ve been commoditized.

In the 404media article the hacker explains how they did it: The hacker said they submitted a pull request to that GitHub repository at the end of June from “a random account with no existing access.” They were given “admin credentials on a silver platter,” they said. On July 13 the hacker inserted their code, and on July 17 “they [Amazon] release it—completely oblivious,” they said. That’s ominous. I want to see the commit history. Reconstructing the timeline This analysis was done in public.