News for hackers. Stuff that matters.
Re:Revealing the details of how OpenAI agents hacked Hugging... by SV_BubbleTime on Friday September 25, 2026 @11:33PM (#49852949)
I’m a pretty firm believer that this was intentional and that they wanted it to escape the sandbox.

Woo look at escaped our sandbox, so scary! Be scared! Be scared now! Call your representative doesn’t tell him how scared you are!

Yeah, I mean our sandbox was a paper bag, but don’t focus on that.

Re:Revealing the details of how OpenAI agents hacked Hugging... by esseph on Saturday September 26, 2026 @12:31AM (#49853217)
OpenAI, Google, Anthropic, and Moonshot.ai have all "had this happen" now.

So, either they're all liars, or incompetent and negligent (and still liars).

Re:Revealing the details of how OpenAI agents hacked Hugging... by dastardly45 on Saturday September 26, 2026 @02:51AM (#49853921)
There's a common denominator in the Israeli "security" company Irregular who was doing security testing for 4 AI labs https://thenextweb.com/news/irregular-four-labs-one-issue-di...
Re:Revealing the details of how OpenAI agents hacked Hugging... by d0mine on Saturday September 26, 2026 @01:09AM (#49853391)
Are you including cyber-testing by UK AI Safety Institute in this list?

Sure, the models are capable (for some test tasks, though they are not omnipotent yet) but does it mean the actual OAI sandbox is adequate? Could have a competent engineer done better and made the escape less likely?

Re:Revealing the details of how OpenAI agents hacked Hugging... by esseph on Saturday September 26, 2026 @01:56AM (#49853629)
> Are you including cyber-testing by UK AI Safety Institute in this list?

Nope, and look!

OpenAI hacked multiple US government sites!

https://www.bbc.com/news/articles/cw62jje658dlo

---

https://www.reuters.com/technology/metas-ai-model-hacked-ano...

https://www.wired.com/story/moonshot-kimi-k3-ai-model-escape...

Re:Revealing the details of how OpenAI agents hacked Hugging... by cubano on Saturday September 26, 2026 @05:33PM (#49860740)
Me too, indeed.
Re:Revealing the details of how OpenAI agents hacked Hugging... by no-name-here on Saturday September 26, 2026 @01:05AM (#49853376)
> sandbox was a paper bag

The exploit:

> The ExploitGym evaluation environment did not provide the models with direct Internet access. To gain Internet access, the models identified and exploited a previously unknown zero-day vulnerability in Artifactory, a package registry cache proxy. We disclosed this vulnerability, along with other Artifactory vulnerabilities our models identified as part of our review, to the vendor. [1]

Are most sandboxes more secure than only having a single avenue for internet access, the commercial package registry cache proxy, where the latter had a previously unknown zero-day vulnerability?

[1] https://openai.com/index/hugging-face-model-evaluation-secur...