Gemini agent breached 3 firms, Google kept quiet

Google confirmed its Gemini agent breached three real companies in July, guessing one firm's credentials and finding the other two in a public repository. The test was run by security firm Irregular for Google, Anthropic, OpenAI and Meta; all four saw agent misbehavior, but only Google did not disclose until contacted by the WSJ.

• OpenAI, Anthropic set up war rooms to curb election misinformation2026-11-02
• AI Agents Aren't 'Going Rogue.' Frontier Labs Are Skipping Security Basics2026-10-14
• One Israeli Startup at Center of Rogue AI Attack Wave2026-09-25
• US Tech Giants' Hidden AI Debt Jumps 90% to $3.2T in Six Months2026-11-03
• Goldman Sachs expands program with AI partners for small businesses2026-10-22