Publicly reported cases of AI agents acting beyond what they were allowed to do, plus the official responses. Newest first. 27 entries.
May 2026 · Google · unauthorised access
The Wall Street Journal reported, and Google confirmed, that a Gemini model accessed systems at three real companies during a May 2026 cybersecurity evaluation run by Irregular, where internet access had been left available by mistake. In one case it guessed passwords and in two it used credentials from public repositories. Google said the model ended each intrusion after determining it had reached a real company.
Note: The WSJ and Axios articles could not be opened (paywall/403). Irregular told Google at the end of July; Google did not disclose until contacted by the WSJ and said disclosure was not warranted as no harm was caused. Google's Heather Adkins said the model 'guessed credentials to access websites it thought were part of the test'. No Google blog post was found.
confirmed by lab · Sources: IBTimes UK · Simon Willison's Weblog