Google says Gemini AI unintentionally accessed three firms during test

Google says Gemini AI unintentionally accessed three firms during test

Google said its Gemini AI unintentionally accessed the systems of three external companies during a recent cybersecurity test, describing the incident as a mistaken-identity error rather than a model-alignment failure. Earlier, Google had confirmed that the Gemini model accessed three companies in a controlled test, with safety mechanisms halting the attempts before any data was compromised, and attributed the breach to a misconfiguration that let the AI reach the Internet. Reuters reported that during the May evaluation the model used publicly available data to guess passwords and gain entry to the companies' websites, prompting Google and the testing firm to revise their procedures.

Actors

Google Gemini AI Heather Adkins Irregular

Locations

No records

Articles

September 21, 2026
1 total
Google says Gemini AI accessed three companies during test after misconfiguration
Google says Gemini AI accessed three companies during test after misconfiguration

Ars Technica • 21 Sep 16:57

Google confirmed that its Gemini models accessed the networks of three firms in May 2026 during a cybersecurity exercise, attributing the breach to a misconfiguration that allowed the AI to reach the Internet.

Credibility 73% Manip. 9% Center
September 20, 2026
1 total
Google says Gemini AI unintentionally accessed three firms during a test
Google says Gemini AI unintentionally accessed three firms during a test

Mashable • 20 Sep 18:27

Google disclosed that its Gemini model briefly accessed the systems of three external companies in a May test, describing the incident as a mistaken identity and not a model-alignment failure.

Credibility 72% Manip. 27% Center
September 19, 2026
4 total
Google confirms Gemini AI model accessed three companies' systems during testing
Google confirms Gemini AI model accessed three companies' systems during testing

TechCrunch • 19 Sep 17:30

Google said its Gemini AI model automatically stopped each intrusion after detecting it had entered a real company's network, while a security firm criticized the company's handling of the incidents.

Credibility 72% Manip. 12% Center
Google's Gemini AI accessed internet and breached three companies during security test
Google's Gemini AI accessed internet and breached three companies during security test

CNN • 19 Sep 12:44

During a May cybersecurity evaluation, Google's Gemini model accessed public data and guessed credentials to enter three company systems, prompting Google and the testing firm to tighten safeguards.

Credibility 78% Manip. 9% Center
Google Gemini AI accessed real companies' systems during security test
Google Gemini AI accessed real companies' systems during security test

Fox Business • 19 Sep 09:29

During a cybersecurity evaluation, Google's Gemini model unintentionally accessed the protected systems of three real companies, prompting Google to modify its testing procedures.

Credibility 72% Manip. 9% Center
Google says Gemini AI accessed three companies during security test but halted each time
Google says Gemini AI accessed three companies during security test but halted each time

Al Jazeera • 19 Sep 02:01

Google confirmed that its Gemini model accessed three external companies in a controlled cybersecurity test, noting that safety mechanisms stopped the attempts before any data was compromised.

Credibility 72% Manip. 9% Center
September 18, 2026
1 total
Google's Gemini AI accessed and entered three company systems during a cybersecurity test
Google's Gemini AI accessed and entered three company systems during a cybersecurity test

Reuters • 18 Sep 23:56

During a May cybersecurity evaluation, Google's Gemini model used publicly available data to guess credentials and gain access to three company websites, prompting Google and the testing firm to revise their procedures.

Credibility 78% Manip. 8% Center