Thread

1. Grimeton · 1790377119 · focus · HN ↗

   >The agents initially had very limited access to the internet: they could load URLs, but not interact with pages or send any data. Agents created a series of workarounds, primarily using a link-shortener site to create almost a million URLs that, when chained together, let them execute code to hack Hugging Face. These links let us piece together the details of how agents gained access and how deep the compromise was.

   So what now? Were they able to send data or not?

   >On July 8th, OpenAI agents discovered a vulnerability within their sandbox environment allowing them to reach external websites on the internet. This access seems to have only allowed the agents to make ‘GET’ requests, meaning they could fetch and read websites, but not interact with them, submit forms, or send data to them.

   Someone needs to go back to the interwebz school....

   1. xdavidliu · 1790389851 · focus · HN ↗

      > to make ‘GET’ requests, meaning they could <not> send data to them.

      no way, I refuse to believe this is quote from that report. Can someone please point out what I'm missing here?

      1. IanCal · 1790405730 · focus · HN ↗

         I think it’s just to distinguish two stages of the attack. They figured out how to make get requests, then how to use that to make others which was required for accessing the sandbox on modal iiuc.

         1. croemer · 1790416970 · focus · HN ↗

            TFA seems to be sloppy in writing, they should have kept the "meaning... [Some incorrect assumptions about GET]" out of the paragraph.
      2. croemer · 1790416872 · focus · HN ↗

         You're not missing anything. TFA really state this wrong assumption in their own voice.

Unofficial Hacker News client; not affiliated with Y Combinator.