Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Show HN: WoseApp – a social network where every reply is a private conversation(woseapp.com ↗)
    discuss
  2. The wonder of human made art(danieldeboulay.com ↗)
    discuss
  3. Liquid Glass adoptions over and100 apps(liquidglassradar.com ↗)
    discuss
  4. Make an educated guess on Fermi-style trivia questions(playdaily.org ↗)
    discuss
  5. Jemalloc 5.4.0(github.com/jemalloc ↗)
    discuss
  6. Nowmine(nowmine.site ↗)
    discuss
  7. Ask HN: Why have we normalized jobs and soft skills bullshit so much?
    discuss
  8. The Scourge of x86 Emulation(fex-emu.com ↗)
    discuss
  9. Ngrx Inspector(visualstudio.com ↗)
    discuss
  10. Reflections on Trusting Trust, Revisited: Poisoning Self-Modifying AI Coding(arxiv.org ↗)
    discuss
  11. Hacker
    2comments
  12. Anderon (IBM) finalizes $1B CHIPS award for US quantum foundry R&D(ibm.com ↗)
    discuss
  13. A Bitter Lesson for Data Filtering(arxiv.org ↗)
    1comments
  14. Mojo 1.1: the compiler now accepts contributions(modular.com ↗)
    discuss
  15. Show HN: Continuity – project state your AI sessions can't silently contradict(github.com/vikcena01 ↗)
    discuss
  16. Show HN: Free Tournament Bracket Maker and Generator(snapbracket.com ↗)
    discuss
  17. macOS 27 is a lifesaver for killing leftover AI Agent processes(9to5mac.com ↗)
    2comments
  18. The Provenance Tax: How LLM Watermarking Changes AI Agent Behavior(lasso.security ↗)
    discuss
  19. Waymo in Singapore(waymo.com ↗)
    1comments
  20. The Concerns Surrounding Rapid Rise of AI and What We Should Do About It(medium.com/f9121212 ↗)
    discuss
  21. Age of Beyond [video](youtube.com ↗)
    discuss
  22. Natural General Intelligence(naturalgeneralintelligence.ai ↗)
    discuss
  23. Youper is shutting down – What kills mental health AI?(youper.ai ↗)
    discuss
  24. Show HN: Free GitHub Action that scans PR diffs for malicious code, not quality(github.com/marketplace ↗)
    discuss
  25. The Bitterest Lesson(typesafe.ai ↗)
    discuss
  26. Google announces new experimental "CC" AI agent for families(arstechnica.com ↗)
    discuss
  27. Show HN: Green Screen Remover – free in-browser chroma key, nothing uploaded(greenscreenremover.net ↗)
    discuss
  28. I built the fastest PHP webserver in the world(qbixserver.com ↗)
    discuss
  29. Data
    discuss
  30. Running OpenBAO on Kubernetes with a CloudNativePG PostgreSQL Back End(cncf.io ↗)
    discuss

Hacking OpenAI

79 pointsby 1h agohacktron.ai
25 comments
44m agoHN ↗

I really hope those model weights are more secure than this

43m agoHN ↗

$6 500 bounty for this is a joke. The black market price would be smth like $6 500 000 or more

36m agoHN ↗

That's why people like doing bad things. It pays. Why do you think movies like using this single theme over and over again? It's always happening

27m agoHN ↗

I suspect you don’t really know what you are talking about. “It pays.” is not the only reason people like doing bad things. You’re right about the movies bit though, people tend to like black and white narratives as your naive “That’s why people like doing bad things. It pays.” comment perfectly demonstrates.

18m agoHN ↗

Valuations for server-side vulnerabilities are low, because vendors don't compete for them.

Why don't they?

17m agoHN ↗

Okay, then first download all their sources (perhaps with model weights?) and sell that. Not the bug itself

12m agoHN ↗

Now you're not selling a vulnerability, you're planning a heist. That is a thing you can do!

30m agoHN ↗

I also thought that's crazy. Why even bother for these kind of bounties.

15m agoHN ↗

Per the article, that's the price OpenAI is willing to pay for an exploit that covers any account or integration one connects to their OpenAI account. Let that sink in.

I don't think the other commenters mentioning how server-side vulnerabilities aren't as lucrative in the black market are making that connection.

41m agoHN ↗

This whole blog-post is impressive with the chain of vulnerabilities involved. However...

OpenAI also paid us a $6,500 bounty.

?

That amount for this payout is beyond pathetic for a near $1.2T company, who just got themselves breached with a complete potential source code leak.

This is like getting close to breaching the main monorepo at Google: google3.

If this was on the black market and the leak included unreleased models and training material, it would easily be worth tens of millions. Even reporting crypto smart contract flaw pay way more than that on average of $100k - $10M.

Come on.

35m agoHN ↗

The unfortunate truth of doing the right thing. Also, correct me if I'm wrong but there are too many bad things out there and companies can't give 1 million bounty for stuff like that. I'm sure they could but in the long run, wouldn't it be unsustainable?

31m agoHN ↗

How much would a nation state pay for a complete copy of OpenAI’s github repositories? I doubt there are many full chains laying around like this.

30m agoHN ↗

No more unsustainable than these companies already are by default. The bounty should have been proportionate to how important and pressing the findings were.

28m agoHN ↗

It’s an interesting bet then.

Pay next to nothing every time, accept one financially-depressed researcher sale to blackhats causing tremendous business disruption every n years. Cheaper than honest payouts to [keep] researchers [honest]? Keep paying chump change. (Booo)

27m agoHN ↗

My guess is that OpenAI has done a lot more to prevent exfil of their model weights than the codebase of their main web app and client.

38m agoHN ↗

...researchers found a bug in the way that the community-discussion forum Discourse processed certain image files. The researchers had access to a special version of Claude Opus 4.8... >At first, it didn’t work. That evening, however, Anthropic released Opus 5 and by the next day, Claude had found a way to exploit the bug...

Is this speed of capability because hacking is almost entirely machine verifiable, thus training quicker/deeper than other domains?

36m agoHN ↗

Interestingly, the vulnerable code had been changed upstream the previous year, but the commit was not documented as a security fix and received no CVE.3 This might be a reason why Debian 12 and 13 have not received the security relevant backports in time.

Ooof, keeping packages like this up to date with the rate of updates and churn is a mess.

21m agoHN ↗

There was something I was hoping to find in the article, which is this common situation where employees are also the customer of their companies product, they happen to have elevated privileges and yet the credential rules applicable to those accounts are same as regular customers. This is across all the product lines, some companies do a better job than others but its still a problem that exists and gets exploited.

16m agoHN ↗

Unsandboxed ImageMagick is known for being a security nightmare even back when PHP ruled the world (not saying sandboxing is a panacea either, it just requires a different and potentially harder exploit to develop a full chain). Difference is it's easier than ever to turn vulnerabilities into full compromises. At some point we'll have to replace all parsers with something at least as safe as https://github.com/google/wuffs right? Otherwise ImageMagick and co. will just keep giving.

5m agoHN ↗

It does make me wonder how much this could be hardened by, to put it in an extremely crude way, taking the current imagemagick code base and throwing a bunch of adversarial SOTA LLMs at it to discover 'bugs' and exploits of this nature until it can be coaxed into a less dangerous state. Or even using the LLMs to fully port its functionality to a memory safe language. Would take a while to get all the changes approved and then into various distribution imagemagick packages.

9m agoHN ↗

They used a heif payload to get server access but they never describe the SSO flaw they used to actually get repo access (the juicy part!), bummer!

Wish they shared that interesting piece since that's the interesting part.

Also pretty shocking that openai uses github. I would have expected a company of that size with that much to lose would be using self hosted stuff.

3m agoHN ↗

agreed… why can an ID token for a separate client application be used to read and write to GitHub? that’s the story here.

9m agoHN ↗

Interesting that Claude agreed to assist in crafting this exploit. Don’t these models usually reject such requests?

6m agoHN ↗

You ask it differently. One could call this "prompt hacking", even.