Thread

1. asciii · 1790395046 · focus · HN ↗

   Running in a "Sandbox"...but agent can still send GET requests? Whaaat

   1. rfw300 · 1790398319 · focus · HN ↗

      My understanding from this report is that the zero-day vulnerability the agents exploited within Artifactory only allowed for GET requests. So the agents used this bankshot HTML sandbox + screenshot site to turn GET requests into arbitrary HTTP request ability.

      One thing the report leaves unexplained, but is curious to me, is that the agents were able to create links on a shortening service with only GET requests? Or did they bootstrap into that by first creating a sufficiently small program on the HTML sandbox that could POST to the link shortener?

      1. asciii · 1790450685 · focus · HN ↗

         > 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.

         Yeah to me it's more like the sandbox wasn't monitored at all. In their observability setup...did they not catch all these urls, multi get requests, chaining etc from the sandbox per se?

Unofficial Hacker News client; not affiliated with Y Combinator.