How OpenAI is defending ChatGPT Atlas from attacks now - and why safety's not guaranteed

An 'automated attacker' mimics the actions of human hackers to test the browser's defenses against prompt injection attacks. But there's a catch.

Dec 23, 2025 2

How OpenAI is defending ChatGPT Atlas from attacks now - and why safety's not guaranteed
An 'automated attacker' mimics the actions of human hackers to test the browser's defenses against prompt injection attacks. But there's a catch.
Read More