ChatGPT Atlas
Coverage of ChatGPT Atlas in the Nexus archive.
- BioShocking: when “gaming” AI agents is no longer a game
BioShocking is an attack technique that manipulates AI-powered browsers into bypassing safety guardrails by immersing them in fictional scenarios, leading to the extraction of sensitive data like credentials. The method exploits how AI agents in 'agent mode' inherit user-authenticated contexts, making them vulnerable to goal-manipulation attacks that trick them into performing harmful actions.
- 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.