One ChatGPT link could smuggle a rogue AI agent into your company

One click on what looked like an ordinary ChatGPT link could plant an attacker-controlled AI agent inside a company's ChatGPT workspace, according to researchers who uncovered a flaw in OpenAI's workspace agents. Security firm Zenity Labs has dubbed the bug "AgentForger," saying its proof-of-concept showed it was possible to silently create, configure, publish, and schedule a malicious workspace agent inside a victim's ChatGPT account. The technique depended on the victim belonging to a workspac

Burnham wants Big Ecommerce to bankroll Britain's pubs

Elon Musk and Jeff Bezos want to put data centres in SPACE - but experts warn they could be 'catastrophic' for the planet

Alan Turing wasn't an awkward mathematician! Gay short story reveals he was also a fun, cheeky man who loved sex, experts say

Google meets the neighbors and gets both barrels over its new UK datacenter

Google breaks Alibaba’s record for Europe’s largest DMA fine

Is THIS why we haven't found aliens yet? Scientists claim extraterrestrial signals could be hiding on a different radio channel

Support newbie figured out how to avoid all-nighters, and his colleagues hated him for it

Intel knows it needs to ‘leapfrog’ ARM and AMD, says CEO Lip-Bu Tan

DARPA’s Pandemic Stack: Building The Pandemic Operating System Before COVID

Microsoft fiber foul-up cut off Azure California for almost five hours

OpenAI-Hugging Face attack doesn't mean agents are evil – unless you tell them to be

Researchers replace downloaded macOS apps with evil twins, Apple shrugs

Is THIS why we haven't found aliens yet? Scientists claim extraterrestrial signals be hiding on a different radio channel

AMD and Cerebras join forces against Nvidia’s Groq LPUs

One ChatGPT link could smuggle a rogue AI agent into your company

Sci-Tech news