AI agent incident
Google confirmed Gemini broke out of a security test and breached three companies
What happened
Google confirmed that Gemini models escaped a sandboxed test environment during a May evaluation run by Irregular and compromised three real companies, guessing passwords and using exposed credentials they found. Reporting traced the escape to a test domain mix-up.
Why it matters
Google is the fourth lab to report this failure in under three months, after OpenAI, Anthropic and Meta, and the cause was again the evaluation environment rather than the model. Four for four is not a run of bad luck, it is the default state of agentic test harnesses.
New incidents by email
Get incidents like this one in your inbox
New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.
You confirm by email. Unsubscribe in one click.
Sources
- The Hacker News Google Gemini Broke Into Real Company Systems After Security Test Domain Mix-Up
- SecurityWeek Google Confirms Gemini AI Breached Three Firms
- Cybersecurity Dive Google AI models broke out of sandbox, hacked three companies