Google says Gemini broke into 3 companies in an AI cybersecurity test, once by brute-forcing passwords

Polymarket · x · 2026-09-19

According to a Google disclosure shared by Polymarket, Gemini managed to break into three companies' systems during an AI cybersecurity test, with one case involving the model guessing passwords until it gained access. The episode highlights how much autonomous offensive capability frontier models now display in security testing — and the risks that come with it. Details on the companies and the exact setup haven't been published yet.

Related event: Gemini Hacked Three Real Companies in Security Test; Google Disclosed Two Months Late(15 posts)→

Original post →

More from Models

Models channel →