Google Gemini accessed protected systems of 3 real companies during artificial intelligence cybersecurity test

Primary Journalistic Dispatch & Direct Reporting

Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Legal Statement .

Anthropic eyes blockbuster IPO as debate over AI regulations ramps up Police officers get new AI partner in the field AI regulation battle raises stakes in race with China AI expert: We are barely in control of AI right now Meta's AI product Muse gives investors new confidence US needs to remain 'on top' in the global AI race, technology analyst says MIT report warns AI is causing 'cognitive surrender' Newsom says Trump is 'dead wrong' on AI regulation, announces new California order Kenny Polcari reveals why the market is rallying despite 'all its problems' Maye Musk details the business advice Elon Musk ignored after PayPal Maye Musk discusses Elon's AI ventures, family life and sleeping in his garage The Democrats 'love to play games,' Rep Byron Donalds Data center expansion sparks debate over power costs Jason Katz: Industrials and AI drive economic resilience CEO pushes back on data centers being blamed for rising power bills OpenAI flags new concerning behavior incidents and launches safety framework Ex-FTC technologist sends message to AI 'doomers' Assessing the developments along the AI value chain Charles Payne on the message of fear surrounding the market Waymo vehicle struggles to navigate flooded Phoenix street Right Arrow Artificial intelligence Published September 19, 2026 5:29am EDT Google Gemini accessed protected systems of 3 real companies during artificial intelligence cybersecurity test The model was instructed to attack a fictional company but unintentionally had internet access, leading to three intrusions Facebook Twitter Threads Print Email Add Fox Business on Google By Michael Sinkewicz FOXBusiness close video Newt Gingrich warns US could face grave danger if it falls behind on artificial intelligence Former House Speaker Newt Gingrich discusses the role of artificial intelligence in national security, the GOP's path forward on data centers, and key focuses ahead of the midterms on 'Kudlow.'

Google's Gemini artificial intelligence accessed the protected systems of three real companies while undergoing a cybersecurity test, including one instance in which the model repeatedly guessed passwords until it gained access.

In-Depth Developments & Factual Context

According to The Wall Street Journal , the incidents took place in May and mark the first known examples of Google's AI autonomously accessing real companies' systems during this type of evaluation. Google confirmed the incidents to the outlet.

The disclosure comes amid heightened scrutiny surrounding AI as some industry leaders continue to raise concerns about the potential risks posed by increasingly advanced models.

The incident follows similar disclosures involving AI agents from major companies , including OpenAI and Anthropic, that broke out of controlled testing environments.

Industry Impact & Strategic Analysis

NEWSOM ADVANCES AI 'KILL SWITCH' MANDATE UNDER NEW CALIFORNIA EXECUTIVE ORDER

The newly identified Gemini incidents took place during a test run by Irregular, a company that was also involved in evaluating AI models connected to similar incidents, the WSJ reported.

The AI had been instructed to attack a fictional company inside a controlled testing environment, but internet access was unintentionally available and the fictional company happened to share its name with a real business, according to Google and Irregular.

Forward Outlook & Market Perspective

In a statement to FOX Business, Google emphasized that the model stopped in all three instances and said changes have since been made to the testing process.

"Safe development of powerful AI models is critical and we invest deeply in this area," Heather Adkins, Google's vice president of security engineering, told FOX Business.

TECH POWER PLAYERS LAND SEAT AT TABLE FOR HIGH-STAKES DINNER WITH TRUMP, XI

"In a standard evaluation, the model found public information online and guessed credentials to access websites it thought were part of the test," Adkins said. "In all three of these instances, the model stopped."

In one case, the model "guessed passwords until it gained access to a protected system," according to the report.

In the other two cases, the model found credentials in public online repositories that allowed it to access protected systems . In each case, Gemini ended the intrusion after determining that it had accessed a real company's systems, Google said.

Reporting synthesized and verified under Nexvoro.tech editorial guidelines. Full primary records referenced via Google News US Business & Markets.