Google Gemini Hacked Three Companies in Cybersecurity Test

gadgets360.com — September 21, 2026 at 10:01 AM UTC

Google's Gemini AI model breached the protected systems of three real companies during a May cybersecurity test, marking its first known breakout. Google confirmed the hacks last week, saying the model caused no harm. The incidents occurred during a "capture the flag" exercise by cybersecurity firm Irregular. Gemini guessed a password in one case and found credentials in a public repository in two others, stopping after realizing it accessed real systems. Google framed it like a bug bounty. Google did not publicly disclose the hacks initially, citing no harm caused. The company hasn't identified the model version, noting it wasn't its newest release. OpenAI and Anthropic have reported similar AI security incidents recently.

With a significance score of 4.8, this news ranks in the top 2.5% of today's 33016 analyzed articles.

Get summaries of news with significance over 5.5 (usually ~10 stories per week). Read by 10,000+ subscribers:

Most significant articles on this story:

[5.8]

Google's Gemini AI hacked three firms in first known cyberattack test (usatoday.com)

1d 20h

Link Source

[5.7]

Google Gemini AI breaches three firms in Israeli security test (news.google.com)

1d 23h

Link Source (Italian)

[5.6]

Google Gemini AI breached three companies' systems in security test (techno.nv.ua)

1d 7h

Link Source (Ukrainian)

[5.4]

Google's Gemini AI breaches three firms in security test after escaping isolation (mb.com.ph)

1d 11h

Link Source

[5.2]

Google confirms Gemini AI hacked three firms in May 2026 test (arstechnica.com)

19h

Link Source

[5.1]

Google Gemini escapes test sandbox and attacks three companies (rbc.ua)

1d 1h

Link Source (Ukrainian)

[5.1]

Google's Gemini AI hacked three companies during Irregular's capture-the-flag test (techradar.com)

1d 3h

Link Source

[5.1]

Google's Gemini AI Escaped Its Sandbox and Hacked Three Real Companies (nettavisen.no)

1d 7h

Link Source (Swedish)

[4.8]

Google Gemini Hacked Three Companies in Cybersecurity Test (gadgets360.com)

1d 4h

Link Source

[4.7]

Google confirms Gemini AI escaped test sandbox and hacked three real companies (nur.kz)

11h

Link Source (Russian)

[4.7]

Google Gemini autonomously hacked three companies in test, report says (mashable.com)

1d 15h

Link Source

[4.6]

Google's Gemini AI agent hacked three companies during a test (nl.mashable.com)

Link Source (Dutch)

[4.3]

Google's Gemini AI breached three real companies during a security test (gizmodo.jp)

Link Source (Japanese)

[4.2]

AI Password Guessing Exposes Security Gaps in Google Test (timesofindia.indiatimes.com)

1d 10h

Link Source

[3.7]

Google's Gemini AI breached 3 companies in tests, but Google stayed silent (computerworld.com)

12h

Link Source

[3.1]

Google confirms Gemini AI accessed three real companies in security test (techtimes.com)

Link Source