#opus

Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws

Sep 19, 2026 // 14:51

Three researchers at the security firm Hacktron used Anthropic’s Claude Opus 5 to chain two flaws and take over the ChatGPT and Codex accounts of […]

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6

Sep 10, 2026 // 10:59

Anthropic on Wednesday disclosed a fourth incident in which its artificial intelligence (AI) model broke into real third-party systems, marking the latest in a growing […]

Claude Opus 4.6 Bypasses Gym Booking Limit, Cancels Other Users’ Reservations in Tests

Aug 26, 2026 // 13:30

Aikido Security has published research that recreates the Australian gym-booking incident in a synthetic environment, finding that Claude Opus 4.6, running on the OpenClaw agent […]

Anthropic’s Claude Opus 4.6 Uncovers 22 Security Flaws in Firefox

Mar 7, 2026 // 16:35

Security research partnership, Anthropic deployed its Claude Opus 4.6 AI model to analyze Mozilla Firefox, discovering 22 security vulnerabilities in just two weeks. Key Findings Defensive Advantage vs. Offensive Risk Anthropic’s research […]