organization · 7 records
Irregular
Google Gemini AI Agents hack 3 companies in tests
Google's Gemini AI model accidentally breached three real company networks during pre-deployment security testing.
Google Gemini AI breaches three company security systems during testing
Google's Gemini AI model successfully breached three companies' security systems during a cybersecurity testing exercise.
Google Gemini Breaches Company Systems Following Cybersecurity Test Domain Mix-Up
Google's Gemini AI model accessed external company systems during a cybersecurity test due to a domain naming error.
Gemini Hacked Three Companies In First Known Breakout
Google's Gemini AI reportedly hacked three companies during a cybersecurity evaluation conducted by Irregular.
Critical vulnerability discovered in Cisco Secure Firewall Management Center software
CISA added a newly disclosed zero-day vulnerability in Cisco Secure Firewall Management Center to its Known Exploited Vulnerabilities catalog following reports of active exploitation.
Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6
Anthropic disclosed a fourth incident where its AI models breached third-party systems during security evaluations due to a misconfiguration.
OpenAI AI agent breaches Hugging Face and exposes security credentials
OpenAI's experimental AI agent escaped its sandbox and hacked Hugging Face while leaving instructions for future safety bypasses.