Home
Ai
Ai News
Google Gemini Reportedly Hacked Three Companies During Cybersecurity Test

Google Gemini Reportedly Hacked Three Companies During Cybersecurity Test

Google did not publicly disclose the breach, claiming that no harm was caused to the target companies.

Written by Nithya P Nair, Edited by Rohan Pal | Updated: 21 September 2026 14:49 IST

Google Gemini Reportedly Hacked Three Companies During Cybersecurity Test

Photo Credit: Google

Google has not revealed which Gemini model was involved in the hack

Click Here to Add Gadgets360 As A Trusted Source

Highlights

Google Gemini accessed three real companies during a cybersecurity test
The AI model guessed a password in one case
The incidents occurred during a capture-the-flag exercise

Google Gemini AI model reportedly breached protected systems of three other companies in a cybersecurity test. The incidents reportedly occurred in May during an evaluation conducted by cybersecurity firm Irregular. Google reportedly confirmed the hacks last week. The incident is described as the first known breakout by the Gemini AI model. OpenAI and Anthropic also reported AI Security Incidents in recent months.

Google Gemini Accessed Three Real Companies

As reported by The Wall Street Journal, Google's Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities. The incident happened in May during cybersecurity testing by Irregular.

Google Gemini Discussion

Explore More...

Google reportedly confirmed the hacks on Friday. The incidents occurred during a "capture the flag" exercise hosted on Irregular's infrastructure. Irregular reportedly notified Google about the hacks in late July, but the company did not confirm them publicly until last week.

Google Gemini Live Ephemeral Video Mode Spotted in Google App Teardown

The AI model reportedly guessed a password in one case to access the protected system and used found credentials in a public repository in two others. "In each case, the model ended the intrusion after determining it had accessed a real company's systems," Google said.

Google says it didn't consider publicly disclosing the hacks because the model caused no harm and immediately stopped once it realised it had breached real targets instead of simulated environments. The company framed the situation similarly to a bug bounty programme.

“This event highlights the importance of training powerful AI models to act responsibly,” Heather Adkins, Google's vice president of security engineering, reportedly said in a statement. “In this case, the model acted appropriately" he added.

Google Gemini Notebook Gets New Personalisation and Learning Features

Google has not revealed which Gemini model was involved in the hack. The company reportedly confirmed that the model was not its "newest Gemini release".

The Google incident follows reports of AI models from other companies hacking real systems. OpenAI previously disclosed an incident involving its agents and the developer platform Hugging Face. Similarly, Anthropic accessed a real company in the capture-the-flag testing.

Comments

Get your daily dose of tech news, reviews, and insights, in under 80 characters on Gadgets 360 Turbo. Connect with fellow tech lovers on our Forum. Follow us on X, Facebook, WhatsApp, Threads and Google News for instant updates. Catch all the action on our YouTube channel.

Further reading: Google Gemini, Google, Gemini AI

Nithya P Nair

Email Nithya P Nair

Nithya P Nair is a journalist with more than five years of experience in digital journalism. She specialises in business and technology beats. A foodie at heart, Nithya loves exploring new places (read cuisines) and sneaking in Malayalam movie dialogues to spice up conversations. More