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

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

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.

Swag packages like these are a token of appreciation not a reward.

The front page post in HN here is worth far more than few thousand dollars , don’t think either organization is operating under purely financial transactional nature .

Most people who find a dropped wallet will return it without evaluating the market value of your compromised identity or the contents of the wallet .

Grateful owners may buy you a beer that doesn’t make them cheap , not everything is evaluated in purely money terms, and that is a good thing ?

Thank you for pushing back on one of the top disruptive bad-faith comments we see on HN.

The follow up arguments will be that since billion dollar companies ultimately only care about their bottom line, so should we.

I'm certain most of these comments mean well (to "open eyes" or whatever), but some of them really are on principle and blatant astroturfing.

The follow up arguments will be that since billion dollar companies ultimately only care about their bottom line, so should we.

so it should be fought by giving them free work in the hopes that they'll finally feel guilty and then start paying proper bounties?

like to me that just seems funny, as if they'd change anything if we'd keep rewarding them for not doing the right thing

like, there's a reason regulation exists for all kinds of shit because otherwise companies would do all kinds of atrocities in hopes of cutting costs

Wallets usually belong to real people with lives. We can empathize with them. Companies are not people. And they also don't and can't empathize with you.

"and can't empathize with you" - I don't really understand why such a perception of companies has been regurgitated and reinforced so much in US public, to the point where it's a blank excuse from ever expecting such a thing from a company. It's not true that it can't. The only reason to keep repeating that kind of worldview is to absolve companies behaving in shitty, toxic or downright evil ways.

The law doesn't say companies MUST choose the most profitable choice at every turn, and even explicitly allows for good treatment of customers, community, employees etc as a viable business strategy (even if it's sad that it must be justified in that way).

I think the point is that companies are purely legal entities, and as such, cannot feel, much less empathize, simply by virtue of them not being living things

The front page post in HN here is worth far more than few thousand dollars , don’t think either organization is operating under purely financial transactional nature .

not always, especially if its just someone independent. iirc there was a guy here not too long ago who started dropping Windows 0days because Microsoft couldn't be assed to process his bug reports

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.

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.

[1]: https://news.ycombinator.com/item?id=49699402

[2]: https://news.ycombinator.com/item?id=49705036

i quite liked using strix. last time i tried it, deepseek was a mess and bloated the context with nonsense. that was ~5 months ago, i wonder how it performs now

This sounds interesting and twisted in some sense

1. A start up is validating a service provider to ensure that they are secure enough so that they can trust them before signing up for their service

2. The service provider is already trusted by so many big name companies who handed over their data, the customers data to them

Should it not be other way around?

On a different note, the finding is not just one off absolute, rather its a symptom which points to certain experience and expertise level for security practices. To be fair its hard to blame the start up folks, they are running against time and cutting corners is somewhat critical for survival for their business

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.

Let us know if you have any feedback!

If I enter an address to "Start testing", I expect at least a preview of the report rather than being dumped on the signup page.

Yeah understood — we need to make sure you own the domain first though

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.

Baseten carries the Soc 2 Type II and HIPAA Compliant logos on its front page. They also have logos for customers including: OpenEvidence (medical related, used by almost 2/3 of physicians in the US, claim HIPAA compliance), Harvey (legal related, claim "binding terms on data protection, data access, incident response SLAs, and other controls aligned with SOC2, ISO, GDPR and other standards.")

From TFA:

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.

The image build dated to March 2023, and the token still worked when we found it in July 2026.

What are the legal implications here?

Given the build is from 2023 one would expect that at least the token would have been rotated, and I suspect some of these compliance checks do require rotation of tokens/passwords.

That said, the whole compliance industry is a joke.

I wonder what model was used for this. Also as far as I know Baseten does not have any abliterated models in their repertoire.

Either Mythos 5.1 or GPT 5.6 Cyber (aka. GPT Daybreak Red)

Neither, actually :)

The bot snippets talk claudish. I'd say Opus 5. But they must be Cyber Verification Program approved by Anthropic I suppose for the LLM not to block them.

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.

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.

IAAL (not legal advice, consult a lawyer in your jurisdiction). You really do not want to pen-test a target without their permission. If you're identified as a culprit, the Feds will shove the CFAA so far up your ass you'll need a proctologist.

as a lawyer, can you speculate as to why anthropic/openai aren't facing many or any consequences for their agents? I'm not asking in a "grab the pitchforks" way. more out of genuine curiosity as my uninformed recollection of the CFAA is as you describe it.

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).

It's not, in most juridictions at least

What did I miss they did that's illegal? It looked like it downloaded a public docker image, searched around inside, and verified that the key it found was still valid (without making any changes), and then immediately notified them about the issue.

If there is anything that was a crime (and it totally depends on jurisdiction), it was verifying the key. They used it to see what it could access, and by using it they had unauthorised access to a system

We build Strix, an autonomous hacking again.

But... we're a security company.

So... we pointed Strix at *.baseten.co and let it run without credentials or source code.

lawyers wet dream. and a perfect case. A security company who KNOWS the law unleashed an AI agent to violate the laws

A lawyers wet dream is when a security company.... Finds an issue, does not abuse it, and reports it to the affected party for it to be patched?

I feel like people like you are more of a lawyers wet dream, in that they'll happily litigate a frivolous case for you while billing you hourly.

Just signed up for strix, is it common for these type of products to want access to my Github repo's? Shouldn't the attack surface be outside them?

So often recent breaches involve Github in one way or another. How is it still considered a sane choice to host anything proprietary there? If your business is built around open source, ok, put a mirror on Github. But CI/CD, gitops, FDEs' stuff have no place on a public cloud. C-level execs may not know bits from bytes, but by now they should've understood that this is akin to storing ammonium nitrate in the open air.

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.