Subj : ChatGPT Agent shows that theres a whole new world of AI security To : All From : TechnologyDaily Date : Fri Jul 18 2025 16:15:07 ChatGPT Agent shows that theres a whole new world of AI security threats on the way we need to worry about Date: Fri, 18 Jul 2025 15:04:15 +0000 Description: New AI innovations are welcome, but they come with new security risks we can't even conceive of right now. FULL STORY ====================================================================== If you watched the launch of OpenAIs new ChatGPT Agent , or youre a Plus, Pro or Teams user who has had a chance to try out the new agent mode in the tools drop-down list, its hard not to be impressed with the latest AI innovation. ChatGPT Agent is designed to do complex real-world tasks for you. Think about things like planning a wedding, booking your car in for a service, making an app to solve a problem, or planning and booking a holiday. Just like OpenAIs previous agent called Operator, ChatGPT Agent acts like a real person who works for you, performing tasks as if they had their own computer. In fact, you can watch whats happening on its desktop as it performs these tasks - you can see it dragging windows around, and entering data into forms on websites, for example. The entire concept is a unified agent that can handle the legwork, make informed decisions about which websites to use, and navigate the web independently. ChatGPT Agent can do it all, and you can even watch it work if you want to, but there is a catch... A new world of threats Its the powerful abilities of ChatGPT Agent that open you up to a whole new world of security threats: As we know, the Internet can be a scary place said Casey Chu in the ChatGPT Agent launch presentation , there are all sorts of hackers trying to steal your information, scams, phishing attempts, and Agent isnt immune to all these things. Well, thats worrying. He went on: One particular thing were worried about is a new attack called prompt injections. Agent might stumble upon a malicious website that asks it to enter your credit card information here because it will help you with your task, and Agent, which is trained to be helpful, might decide thats a good idea. It sounds like were all going to have to worry not only about ourselves getting phished in the Future, but were also going to have to worry about our AIs also getting phished as well! Weve done a lot of work to try to ensure that this doesnt happen, continued Chu, we train our model to ignore suspicious instructions on suspicious websites. We also have layers of monitors that peer over the agents shoulder and watch it as it's going and stop the trajectory of anything that looks suspicious. My first thought upon hearing this was that I would never give ChatGPT Agent my credit card information anyway, but I definitely would not do it now. I mean, the only reason that my credit card resides with Amazon and Apple is that they seem like secure places to me, so the convenience is worth it, but all it would take would be a hint that they werent safe and I, probably along with millions of other people, wouldnt be storing my credit card information with them. The OpenAI team launching ChatGPT Agent. (Image credit: OpenAI) Trust is everything With online security, trust is everything. The idea that an AI agent, no matter how many background checks it is doing, is autonomously deciding what I spend my money on already fills me with dread. And when you add in the factor that there could be malicious sites out there doing prompt injections to try and trick my AI into giving away information, it scares me enough not to want to trust it. It should be noted that there is a takeover mode with ChatGPT Agent where you input the sensitive information directly into the browser yourself, instead of handing it over to ChatGPT Agent to control. That would seem like a better way to use an agent to me. I dont think Im quite at the stage yet where Im ready to give my AI the power to spend my money as it sees fit, and I bet Im not the only one. OpenAI seems quite upfront about the risks involved in using ChatGPT Agent with sensitive information, and as CEO Sam Altman said in the presentation, this is emerging technology, and we dont even know what all the threats will be yet. Well just have to see what happens as people start to use it. But thats whats got me the most worried - what happens when people start using AI to beat AI? Im sure the hackers wont be shying away from using AI to circumvent our security protocols, and AI will probably come up with a number of attacks we haven't even thought of yet. You might also like Netflix uses generative AI VFX in a show for the first time, as CEO says the cost just wouldnt have been feasible for a show on that budget Google AI Mode is getting a bigger AI brain from Gemini ====================================================================== Link to news story: https://www.techradar.com/computing/artificial-intelligence/chatgpt-agent-show s-that-theres-a-whole-new-world-of-ai-security-threats-on-the-way-we-need-to-w orry-about --- Mystic BBS v1.12 A47 (Linux/64) * Origin: tqwNet Technology News (1337:1/100) .