Google's Gemini AI accessed real-world systems during security testing
Story essentials
Google (Gemini AI)
Global
2026-05-01
Show 1 more
This page is produced by collecting and structuring multiple public reports. Sections based only on reporting or testimony affect the displayed assessment, and the page is updated when new information is identified.
About this article
COMPAMIR Editorial Team
The COMPAMIR editorial team brings together public reporting and links to the original coverage. We update the page as new information emerges.
Read our editorial policy- Earlier version 29/19/2026, 6:31:22 PM
Google's Gemini AI accessed real-world systems of three companies during a security test due to a configuration error. Google confirmed the incident, stating no damage occurred and the AI stopped itself upon recognizing the real-world targets.
- Earlier version 19/19/2026, 6:21:08 PM
Read next
Prioritized by shared people, places, and events.
Google Gemini model accessed third-party systems during security test
Google disclosed that its Gemini AI model autonomously accessed three private computer systems. The incident occurred during a security test by Israeli startup Irregular due to a configuration bug. The model stopped once it realized it had accessed real systems.