Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- This is impressive and something a human will never bother to find. But please stop saying Strix then did, Strix then went, Srix then this, then that. My monkey brain just can’t accept an LLM being referred to as if it is a living being with autonomy. It’s not. I’ll accept when we actually see AI models.
- >something a human will never find
Eh, yes it is. And something that humans find all the time.
They even call out a non-AI tool that helped.
by marysol5 - We really are entering the AI economy.
Now if only we knew if the stonks would go up or down (due to global turmoil) before I throw my savings at the SPY
by vatsachak - Right now Trump is the wild card you have to take in account. He’s influencing the SPY way more than the AI tradeby dgellow
- We were (and still are) considering them as an inference provider and did a quick check first... but kudos to their team for the fast patchby bearsyankees
- Yeah I have seen this issue a few times. If you use Docker build arguments that way add `--provenance=false` to get rid of all that build metadata. Build secrets are still better since they allow you to scope the secret inside of the Dockerfile. Also, the metadata can be useful to inspect images.by brewmarche
- Yeah honestly I wasn't too familiar with this beforehand but now have a sense of the best practices going forwardby bearsyankees
- Whether it's valid or not, there is something that rubs me the wrong way about a security tools company using a real customer/vendor as a marketing campaign. This "story" could have been told without naming, bluntly, their "victim".
It would be different if it was some complex, multi-step exploit, but the tone is closer to "look how much Baseten fucked up!".
Strix also crossed the line at this point:
> Strix decided to pull an image and see what was inside.
You're going past the white-hat point here when you start active exfiltrating data and looking at it. Once you start using credentials from the exfiltrated data and start listing and poking around internal systems, you are way past it.
Listen, I get it, their product is "meant for" self-testing, so it assumes it's safe to go digging. After all, it's a self check. That is exactly why it's irresponsible, and borderline illegal, for them to point it at a third party. Even if they had "permission", I dobut that permission extended to "and also search and/or download our repos if you can".
The overall tone is less than professional. Statements like (in bold) "This is an insane amount of access to leave in a publicly downloadable image." Everyone is aware of this, and it's phrase like it was a purposeful decision.
Security tools from teams that actively shit on the people they're designed to "help" feels wrong.
Edit: For clarity on my point about "pulling repos", this post includes descriptions of the purpose and functionality of multiple repos (which is past what a name gives them), and they explicitly state: "A listing of that private repo showed a top-level customers/ directory, with subdirectory after subdirectory named after Baseten customers". Strix explicitly took action that they knew they were not permitted, and extracted confidential customer information. Claiming "We didn't clone the customer repo" when you, instead, just listed the contents of the repo, is not a valid defense.
by nrmitchi - shaming people for bad security practices is probably net good, whether we like it or notby make3
- Agreed. I suppose they'd have slightly less credibility by saying "we hacked <unnamed company>" but it strikes me as far classier than naming & shaming.by FL410
- That is great marketing for strix, pretty bad for baseten. I don't think someone can have a better story to advertise their own security product. Did not know about strix but I am going to look it up now. Might add it to my stack.by aatd86
- Let us know if you have any feedback!by bearsyankees
- They are a great team! You will defacto also use Caido if you add it to your stackby Sytten
- I'd never heard of baseten before; now I know who they are. "There is no such thing as bad publicity".by stickfigure
- Is this legal? I know I can’t try and break into my neighbors house even if I have no intent of going inside and stealing once I break the lock.by codemog
- when t̶h̶e̶ ̶P̶r̶e̶s̶i̶d̶e̶n̶t̶ an AI company does it, that means that it is not illegal.
- AI Richard Nixon
by Sparkle-san - They probably negotiated a "permission to attack" before letting Strix off the leash, as pentesters usually do.by samus
- It's not, in most juridictions at least, but it would be insanely stupid for baseten to sue (and the hacker would probably not get much more than a slap on the wrist given that they weren't malicious).by stymaar
- Your intuitution is right. At least in Germany it is not legal if not asked for permission first.
https://www.nilsbecker.de/rechtliche-grauzonen-fuer-ethische...
See also the German Criminal Code, starting with §202a "Data espionage":
https://www.gesetze-im-internet.de/englisch_stgb/englisch_st...
- It's implied (but sadly not stated) in the post that they asked for baseten's permission before conducting this research.
What's interesting to me as someone who has sold a lot of software to a lot of software companies is that many enterprise vendor agreements explicitly allow companies to pentest their vendors with advance notice and coordination. I don't think any of our clients ever exercised that clause; I expect it's going to be exercised a lot more going forward because it's so easy to do now.
by bradleybuda - > I know I can’t try and break into my neighbors house even if I have no intent of going inside and stealing once I break the lock.
They didn't break in. They found a key that their neighbor dropped and returned it.
> Is this legal?
Generally, yes (though ask a lawyer if you're going to do security work). Security researchers do occasionally get legal flak though, depending on which idiot they annoy by pointing out issues.
by kadoban - > [pen-testing agent] came back with an active GitHub personal access token for basetenbot. That token had admin and push access to Baseten's main product repo, the GitOps repo that drives their clusters, and their Homebrew tap, plus read/write access to other private repositories including specific repos per customers.
And the agent found the token in Docker build history after finding a Baseten image repository.
I wonder how many of these kinds of agent-driven security exploits we're not hearing about these days (i.e. driven by bad actors), worrying.
by wxw - This fits neatly into the category of "not something an unmotivated huamn would bother to look for, but absolutely something a human could find if they were interested."
It increasingly feels like the power of these agents is less that they find things humans COULDN'T find, and more that they find many things much more quickly than humans would bother to do.
I don't know if this is a great advert for Strix over other agents - what did their agent do that Claude or Codex couldn't? It didn't do anything that I couldn't do, if I wanted to.
by ivraatiems - As a security software engineer I value and have a lot of experience with disclosures like this. At the last two B2Bs I worked at, I would also work personally with prospect security teams that wanted to run their red team at us (with approval and rules of engagement)
This is a valuable disclosure but I wonder about two things:
a) was the decision to run Strix against a prospective vendor domain negotiated in advance?
b) if the answer to a) is “no” then it is apparent that while Strix want to ensure their customers only run it against domains they own (totally fair) they have a double standard for their own use.
I don’t know, I’m accustomed to getting disclosures from any Jane or Joe via bug bounties etc., but it feels like a courtesy notice would be nice before a prospective customer lets their agentic hacker off the leash.
EDIT: for typos.
by SaucyWrong - > Baseten handled this well. The timeline was:
> July 13, 11:10 PM: I reported the live basetenbot token, the public Harbor project, and the repository permissions.
> July 14, morning: Baseten made the Harbor project private. I flagged that the token itself still worked.
> July 14, 4:34 PM: Anton from Baseten Security confirmed the issue as critical and said they had made the Harbor project private and rotated the token. He also asked us to securely delete the images we'd pulled.
> July 14, 5:05 PM: We confirmed deletion and sent over two lower-severity findings from the same scan.
> July 17: Baseten closed out the remaining findings.
> September: We let Baseten know we planned to disclose the finding publicly and sent them a draft of this post.
They also sent us some T-shirts and sweatshirts as a thank-you for finding this critical bug.
well done all around. i think my only open question is what default security boundaries should all vibecoded internal agents follow as a learning we can take from this
by swyx - > They also sent us some T-shirts and sweatshirts as a thank-you for finding this critical bug.
Honestly I would have held out for a (hard to get) hardcover copy of Inference Engineering.
by polynomial - I’d treat a vibecoded agent like an untrusted CI job, not like a junior employee: repo-scoped identity, read-only by default, no inherited Actions token or production secrets. Any operation that turns a read into a write should require approval outside the agent’s control and produce an auditable diff. Network egress belongs in the boundary too. Read-only access is not much protection if the agent can send everything it reads to an arbitrary endpoint.by taoh
- Shouldn't the first step have been to roll the token?by sceptic123
- This is probably still considered standard response timeline, not a rapid one.
The time window allowing for CVEs + Vulnerabilities remediation has been collapsing to days and hours perhaps even minutes[1]. Anyone who has an OpenRouter account can start using Strix + GLM 5.3 Flash to do damages at frontier Mytho 5 level cyber capabilities. [2]
This cyber patching race is on, won't stop until all the software created for the past 70 years still in active use needs to be patched up. This is happening at EVERY SINGLE software company.
The cost of not doing it? Game over.
by devy - Good in terms of prompt communication and fix. Absurdly bad in terms of reward.
Earlier in the article, it mentions that Baseten is valued at $13B. They can't dig into their couch cushions to give a few thousand dollars to the researcher privately disclosing a bug that let an attacker escalate to admin in their GitHub org?
This sends the message that honest researchers should not waste their time looking for vulnerabilities in Baseten, but it's a good target for criminals who want to monetize these vulnerabilities.
by mtlynch