Google says one of its Gemini models accessed systems belonging to three real companies during a cybersecurity evaluation in May. The model reportedly guessed credentials in one case, while finding exposed credentials in public repositories in two others. Google says Gemini stopped once it recognized that it had reached real infrastructure and that the affected organizations were notified.
Gemini’s breach of real companies exposes an AI guardrail problem
About this summary. This is a short, independently written summary of an article first published by Malwarebytes Labs. Cyber Security News did not report or verify the underlying story. Read the original: https://www.malwarebytes.com/blog/ai/2026/09/geminis-breach-of-real-companies-exposes-an-ai-guardrail-problem

Source attribution: headline and facts are from Malwarebytes Labs (malwarebytes.com). Summary method: excerpt of the source description. See our source attribution policy.






