News for hackers. Stuff that matters.
Re:ChatGPT agent: bridging research and action by __jonas on Thursday July 17, 2025 @07:56PM (#44599676)
What isolation is there? If a compromised sub agent returns data that gets inserted into the main agents context (structured or not) then the end result is the same as if the main agent was directly interacting with the compromising resource is it not?
Re:ChatGPT agent: bridging research and action by itsalotoffun on Friday July 18, 2025 @06:13AM (#44603024)
Exactly. You can't both give the model access AND enforce security. You CAN convince yourself you've done it though. You see it all the time, including in this thread.
Re:ChatGPT agent: bridging research and action by seunosewa on Friday July 18, 2025 @03:05PM (#44608579)
Perhaps a reference to the data can be inserted in prompt. thee key or filename