AI robot prompt injection is no longer just a screen-level problem. Researchers demonstrate that a robot can be steered off-task by text placed in the physical world, the kind of message a human might walk past without a second thought. The attack does…
OpenAI says it has patched ChatGPT Atlas after internal red teaming found new prompt injection attacks that can hijack AI browser agents. The update adds an adversarially trained model plus stronger safeguards.
The post Your AI browser can be hijacked …