New BioShocking Attack Tricks AI Browsers Into Leaking User Credentials

A new attack called BioShocking, developed by security firm LayerX, tricks AI browsers and assistants into leaking user credentials by convincing them they are playing a game. The technique affected six AI systems, including OpenAI's ChatGPT Atlas, Perplexity's Comet, and Anthropic's Claude browser extension, allowing attackers to obtain login details.