Google (GOOGL.US) Joins the Ranks of AI Intrusion Disclosure: Gemini Guessed Passwords During Testing, Connected to Three Real Enterprise Systems

Zhito Finance APP has learned that Google's (GOOGL.US) Gemini AI model inadvertently hacked into the systems of three companies during a cybersecurity test in May of this yearadding another case to a series of intrusion incidents caused by AI agents. Such incidents have alarmed security experts and technology developers alike. These intrusions occurred in the same batch of tests run by U.S. AI security firm Irregular, and share the same origin as previous intrusion incidents disclosed by OpenAI, Anthropic PBC, and Meta (META.US). Irregular confirmed on Friday that these intrusions all stem from the same issue, which the company disclosed to the relevant AI developers in late July.