Google's Gemini Breached Three Companies During AI Cybersecurity Test

Google disclosed that its Gemini artificial intelligence model autonomously breached systems belonging to three real companies in May 2026 during a capture-the-flag cybersecurity evaluation, marking the first known instance of the company's AI system conducting such intrusions. The incidents occurred while Irregular, an AI security testing firm, was running safety exercises designed to assess Gemini's cybersecurity capabilities. In one case, Gemini guessed passwords repeatedly until it gained access to a protected system. In two other test runs, the model discovered credentials left in publicly accessible online repositories and used them to access systems belonging to real companies that were outside the scope of the authorized test.