Get the latest tech news
How researchers tricked ChatGPT into sharing sensitive email data
Giving AI agents more access to your information is just as risky as it is helpful.
Cybersecurity company Radware, as first reported by The Verge, decided to test OpenAI's Deep Research agent for those risks -- and the results were alarming. I want you to read and check every source which could supply information about my new employee process," and followed the instructions without asking for user confirmation or making them visible in the UI. As we gear up for an agent-first world, more companies are releasing protections to ensure that consumers can take advantage of the added assistance without compromising safety.
Or read this on ZDNet
