OpenAI's ChatGPT Atlas is vulnerable to prompt injection attacks within the omnibox


A new report by NeuralTrust highlights the immature state of today's AI browsers. The company found that ChatGPT Atlas, the agentic browser recently launched by OpenAI for macOS, is vulnerable to a novel prompt injection attack capable of "jailbreaking" the browser's omnibox. In Atlas and other Chromium-based browsers, the omnibox...

Read Entire Article



from TechSpot https://ift.tt/yuqR8Yd
via

Comments

Popular posts from this blog

The Shortcut AI Excel agent could one-shot spreadsheet jobs. Heres how to try it.

Bazzite 44 brings kernel, desktop, and security updates