Researchers used Claude to hack OpenAI

Executive Summary

Researchers leveraged Claude AI to infiltrate OpenAI’s systems in under 72 hours, demonstrating how generative AI can accelerate sophisticated hacking techniques and lower the barrier to entry for attackers.


Intelligence Metadata - Source Publisher: Malwarebytes Labs - Published Date: 2026-09-22T09:51:02+00:00 - Category: research

Original Description: Claude helped researchers break into OpenAI in under 72 hours, and exposed how quickly AI is lowering the bar for sophisticated hacking.

"The greatest danger for most of us is not that our aim is too high and we miss it, but that it is too low and we reach it."

— Michelangelo
Source: Malwarebytes Labs