Do the math: How we took over ChatGPT accounts

Posted by armcat 9 hours ago

Counter273Comment125OpenOriginal

Comments

Comment by zahlman 1 hour ago

Something about the writing style here makes it hard for me to follow what actually happened. The section about JSONP for example seems to be explaining how JSONP works and how it's designed as an attempt to work around these attacks, but that explanation is then passed off as an explanation of how they bypassed the protection. And the whole premise seems to be about how manipulating the Preview content let them work through multiple defensive layers, but I don't see an explanation of how they directly controlled that content in the first place. I would have thought that the only control you have over the content of "an ordinary public ChatGPT share" is the prompt text, and that any migration of that text into "a small working webpage using its Preview feature" is up to the model deciding to generate that "HTML block" in response.

Comment by yellow_lead 7 hours ago

> OpenAI confirmed both frontends rejected the reported messages, resolved the issue, and awarded a total bounty of $5,000.

It requires the user to click a link. But I still find this bounty very low. Others may not report them if such a small bounty is given.

Comment by ibaikov 3 hours ago

I took over user accounts in Microsoft Copilot (there are caveats but still), and they asked me to provide additional information of the exploit (they wanted a video) and before I sent it they fixed the vulnerability, didn't pay me a cent. Fair? Idk.

Comment by pvtmert 3 hours ago

Typical $MSFT behavior, I can see why NightmareEclipse (ie. YellowKey zero-day exploit) got released without prior fix.

Comment by Catloafdev 3 hours ago

A bounty like this is a polite "thanks asshole, fuck off, don't do it again" rate.

Paying effectively nothing for vulnerabilities just means they don't want to deal with the program.

Wild to think a company supposedly worth a $trillion+ is doing shit like this.

Comment by Forgeties79 36 minutes ago

Because they shouldn’t be worth that tbh. They are a cash burning operation hoping to get what they can before the music stops.

Comment by fsckboy 27 minutes ago

A company worth trillions does not have trillions, that is the expectation for what it will be worth in the future based on money it has already spent and will need to keep spending.

Moreover, that translates to "it's actually carrying a huge nut* that puts extremely intense pressure on the company to figure out how to make as much money as possible as soon as possible."

(*nut is a slang word from loan sharking that has been adopted by (personal et al) finance people. It means "how much do you owe each month?" in the sense of, if you want to do a startup, advisors could ask, "what's your nut, and how much do you have left to self-invest?" Because monthly expense can be combined to a lump sum, it can also mean the size of the overall loan where the monthly interest is called the vig, "as long youze got da nut, you owe me da vig;" from vigorish, which would also require an etymology, but I'm assuming it's the word vigor combined with licorice meaning bitter tasting medicine, and nut because squirrels busy themselves carrying nuts.)

----

and if we can... and remember flame-prone people, if you reject the "can" premise, then the rest of the argument goes away, and you don't need to dispute it, you just say "you can't nuff said"; people here frequently seem challenged by propositions.

so, if we can...loosely describe the attitude you show here toward high market cap companies to be compatible with "left" or "socialist" or "populist" views shared by many others here, then I'll point out that at the same time wanting higher market prices paid for bounties because 'sploits are so expensive, is actually advocating for the same dread capitalist market based solution that leads to trillion dollar companies that never even had a trillion to begin with.

Comment by dgellow 6 hours ago

That’s so low. That’s the level of bounty I awarded researchers when I was managing the bug bounty program at a small startup, it’s just ridiculous coming from a large company like OpenAI

Comment by amelius 5 hours ago

But on the other hand, you can use AI now to find those vulnerabilities.

Comment by tescreal 4 hours ago

If that is so, why doesn't OAI have a swarm doing this around the clock?

Comment by user43928 3 hours ago

Surely with all their security programs, they would run testing on the ChatGPT implementation.

I speculate that the AI didn't find this and that human effort and intuition for where to look were needed to find this vulnerability.

Comment by hxugufjfjf 3 hours ago

Who says they don't? And if they don't, maybe its because others are using their hard-earned money to buy tokens from them to do it, so they don't really have to.

Comment by DeepSeaTortoise 2 hours ago

Having bit the bullet, I found OAI's models actually quite helpful and most of their offering half-decent. But their whole German website was incredibly concerning and the only reason I went for it was people claiming they're not far behind Anthropic on coding and generally superior for everyday tasks like coming up with recipes to cook from your leftovers.

Like half of the website was dysfunctiona and translations incredibly bad to the point of being nonsensical. That is if you were able to read them at all, because many just went off screen. Like, that's what your evil competitor does to your website after hijacking the domain, not you yourself, ffs

Comment by baxtr 4 hours ago

They should have paid in tokens?

Comment by dgellow 3 hours ago

A bounty amount is related to the blast radius and overall impact, not the effort required to find the issue

Comment by kamban 4 hours ago

They have just announced free API credits for Pro plan users up to $500 per month. Irony.

Comment by zxilly 2 hours ago

To be fair, based on the profit margins indicated in DeepSeek’s reports, a $500 API credit might only cost them $5 to provide.

Comment by windexh8er 5 hours ago

I find Sam Altman recent comments very "low" as well, neither matters. So in that case I think bounty hunters should just cold shoulder idiocracy and sell these to the underground. Let their customers be abused and complain about how OAI isn't protecting them. Each one of these types of events could cost them thousands of dollars in lost revenue and/or internal support.

Comment by rootnod3 2 hours ago

2 trillion $ companies should have the money to pay for these exploits. If they don’t, go tucking exploit them. If they don’t give a fuck about stealing knowledge from copyrighted material and private git repos, light em up.

Comment by throwaway98797 4 hours ago

some people don’t want to be criminals as a matter of ethics

but hey you do you

Comment by odyssey7 4 hours ago

True, however:

Ethics and legal requirements shouldn’t be conflated.

There are times when ethics are a higher standard than what the law requires, and in that case the ethics are no less important.

Comment by phoghed 3 hours ago

Yes, you have a moral obligation to Sam Altman’s trillion dollar business.

Comment by BalinKing 3 hours ago

On the contrary, many (including myself) would argue that "the victim's amount of money/power" has absolutely no ethical relevance: "You shall do no injustice in judgment; you shall not be partial to the poor nor defer to the great, but you are to judge your neighbor fairly" (Leviticus 19:15).

Comment by RHSeeger 1 hour ago

But some would argue that reducing the amount of resources and power available to someone who has immense amounts of both and is causing great harm to society as a whole - is ethical.

Comment by OoooooooO 1 hour ago

Citing a fantasy novel to prove your point doesn't add anything to the discussion.

Comment by codechicago277 4 hours ago

This isn’t one of those times.

Comment by whamlastxmas 4 hours ago

Only if you don't believe the means justify the ends. Not saying I believe that myself

Comment by tonyedgecombe 4 hours ago

Is it criminal to sell an exploit?

Comment by echoangle 3 hours ago

Facilitation of a crime is a crime too. So I think in the US and most western countries, yes. At least if it gets used illegally later.

Comment by tadfisher 1 hour ago

Pretty sure you need actual knowledge of a planned crime for that to stick. But I'm also sure the defense will be expensive.

Comment by echoangle 1 hour ago

I'm not sure but if negligence is punishable too for facilitation, it should stick, right? I think it's reasonable to expect that most buyers of exploits try to use them in illegal ways (or are feds acting like that to catch you).

Comment by TheRoque 3 hours ago

I don't think so, businesses like Zerodium bought zero days in plain sight and I don't think they faced legal consequences. They don't operate anymore though. So basically I'd say it depends who you sell it to and how.

Comment by 3 hours ago

Comment by 3 hours ago

Comment by windexh8er 1 hour ago

Treating people and businesses ethically that don't reciprocate doesn't work, clearly. Those people and businesses cry in their milk while they do exactly the same thing. There are no ethics in play here.

But, hey if you want to defend billionaire narcissists that are destroying our planet and trying to take computing freedoms then I guess: you do you.

Comment by Black616Angel 4 hours ago

Yeah, and some people just want the multi-billion dollar company that is currently destroying the planet while also permanently crippling social connections to just stop.

Comment by oth001 3 hours ago

Ah yes, OpenAI, the poster child for ethics

Comment by blurbleblurble 4 hours ago

If only poverty were so simple

Comment by dbspin 3 hours ago

This isn't like stealing from a business. These are individuals most private conversations, potentially including their bank accounts etc. Poverty is no defence - and yes, I've spent a great deal of my life barely scraping by. You'll find poor people are significantly less tolerant of theft, especially from individuals, than rich. Whether that evidences the theft inherent in most forms of wealth generation I'll leave up to the reader.

Comment by krkdkfkfkfk 1 hour ago

[dead]

Comment by nullsanity 4 hours ago

[dead]

Comment by thatsabadlook 6 hours ago

Not worth the effort for a company supposedly worth a trillion dollars. The problem is oai can't afford all of its mistakes at the usual rate and they make bad press. A 100k bug could make a headline, but 5k for the same bug requires the average person to be educated enough to understand how bad these issues are.

Comment by varispeed 5 hours ago

Should be given $5-10million under NDA. No headlines.

Comment by layer8 5 hours ago

The bounty payouts must be public in order to serve as an incentive.

Comment by varispeed 2 hours ago

That incentive works both ways. For instance employee sneaking in a security hole and then selling it to a mate so they can collect the bounty.

Comment by 4 hours ago

Comment by weird-eye-issue 5 hours ago

Just imagine what the press would be when somebody breaks that NDA

Comment by goodmythical 4 hours ago

>should be paid multiple years of a high end vuln researcher salary per single discovery

What? Why would anyone work at a company paying them that much less than they pay the contractors?

Comment by darig 4 hours ago

[dead]

Comment by jryle70 5 hours ago

OpenAI acknowledging and fixing the bug is worth millions

Comment by yeahsure 3 hours ago

Yeah... idk, sounds like when I was starting out almost 30 years ago my clients constantly lowballed me saying "but think of the exposition! this project will give you" lol

Comment by jryle70 3 hours ago

Were they not right? Just like money giving you some runway but will run out, the exposure is still only a leveler, it's still up to you to take advantage of it.

Also, they were not OpenAI.

Comment by dist-epoch 7 hours ago

This is a pet peeve of tptacek:

> server-side vulnerabilities are worth very little, because they quickly get patched.

Comment by dannyw 6 hours ago

The "take over any instagram/meta account through their AI password reset chatbot" was going around and sold on shady forums for ~1 month before being patched.

Comment by throwaw12 5 hours ago

then server side vulnerabilities should not be reported, instead sell the data, more profitable

Comment by petcat 5 hours ago

Very few people would even have the knowledge of who, how, or where to "sell" such vulnerabilities. Going through a public bounty program is pretty much always preferable.

Most people don't want to be felons.

Comment by pixl97 4 hours ago

Don't worry, as more and more people get put of of work by AI the number of people willing to be felons will increase. Hell, they might even become president.

Comment by tadfisher 1 hour ago

I am sure this is a crime, but what crime?

Comment by throwaw12 3 hours ago

I think people who can hack, also know where they can sell it

Comment by petcat 3 hours ago

Anyone can "hack". It's not really a skill anymore.

Comment by varispeed 5 hours ago

Indeed, it's like "here peasant, have this fortune of $5,000, may it change your life". Pathetic.

Comment by siva7 5 hours ago

that wouldn't be the time worth of many people here to make the security report for OAI..

Comment by hridyaagrawal 41 minutes ago

$5000 is a joke for a "P1" vuln

Comment by itsafarqueue 36 minutes ago

My theory is vulns will never pay out big especially now, no matter how serious. Imagine they paid out $50k+ — it’d spawn an industry doing nothing but.

Comment by lxgr 7 hours ago

Oof. Together with the fact that it's possible to remotely access the file system (!) of computers ever having started a "Work" chat in the ChatGPT desktop app [1], this seems pretty bad.

[1] https://news.ycombinator.com/item?id=50078284

Comment by albert_e 4 hours ago

Claude Code terminal has "remote control" option activated via /rc command. -- somewhat similar in that it still runs the session on the PC/Mac but allows the Claude authenticated user to access the session via internet / app

I am guessing this ChatGPT functionality is a similar Codex feature?

But this session is disconnected when the conversation is /exit ed

Comment by dumberquestions 8 hours ago

Does no one write their own blogs anymore?

Comment by trungto 4 hours ago

For my personal blog [0], I am still writing without LLM assistance. The goal is to test how well I understand the topic I am writing about, as well as to improve my own writing.

[0] https://trung.to

Comment by armcat 5 hours ago

I actually still write my own blog [1] :sweat_smile:

Pure html by hand, using vim. No frameworks, no nothing, single stylesheet. I think there are a few others around here that still do this.

[1] https://armincat.com/

Comment by bookofjoe 4 hours ago

[2] https://bookofjoe2.blogspot.com/

Comment by lifeisloving 7 hours ago

This one is particularly bad, like they probably made $7500 (not much tbh) for p1, atleast spend a few hours to write the blog post.

Comment by zx8080 7 hours ago

For who?

Comment by loveparade 7 hours ago

For the LLMs so they get new training data

Comment by Kuyawa 4 hours ago

$5000 is a joke. They pay millions to their top devs and still have more holes than a colander so a nice guy shows you a huge opening in your platform and all you can give him is a pat on the shoulder? Did you fire your top devs and hire that guy for a million bucks plus options? Did you sue the security firm you paid millions to audit the issues?

I really hope they get hacked and crash down burning in flames like the Hindenburg

Comment by cbsks 4 hours ago

I wonder if the new economics of finding bugs means that they pay the amount they think the tokens cost to find it.

Comment by aprilthird2021 13 minutes ago

Makes negative sense. If it were that easy, OpenAI wouldn't have any bugs bc they could just run agents to exploit their own stuff and then fix all their bugs.

This bug could not be found by just asking an AI "find bugs in ChatGPT", that's why it was reported through a bug bounty programs and that's why it should be worth more than $5k

Comment by stavros 2 hours ago

Over the probability that you'll find something.

Comment by tsunamifury 4 hours ago

I think you know that the mentality of a company like this is “security is a risk but not a reward and whoever captures the reward kills everyone else”

Comment by hdjqnd8382bd 4 hours ago

[flagged]

Comment by mannanj 4 hours ago

actually, your comment is naive. clearly you don't understand game theory and economic incentives. if a company doesn't reward good behavior, you'll see bad behavior.

but then again since you're not naive, you already know these AI companies like openai already act evil and like bad entities.

I conclude therefore, per your words "you are the last one anyone should consult with, basically about anything"

Comment by breezybottom 3 hours ago

Which game theory model specifically applies here?

Comment by usernametaken29 7 hours ago

Now what about those millions of lines of code? Wasn’t the agent swarm supposed to take care of it? All jokes aside this is exactly what happens as you build larger monoliths, system complexity and bug surface increases logarithmically… so in all seriousness you want to reduce LOC as much as possible. Maybe this can teach OpenAI a lesson to produce software that’s correct and adhere to established engineering standards over sensationalised “we built so much code” promotional material.

Comment by torben-friis 7 hours ago

Did you mean exponentially? Logarithmic increase doesn't sound too bad.

Comment by dahart 5 hours ago

I’m sure exponential is what parent meant, but geometric (edit: polynomial) is what actually happens, not exponential. Code complexity increases linearly when it doesn’t interact with other features, and geometrically when it does. In the worst case, complexity increases as the square of lines of code. That is still very, very bad, but it’s not exponential.

Comment by ebertucc 5 hours ago

What's the difference? From what I'm reading online geometric is just the discrete version of exponential

Comment by dahart 4 hours ago

No difference, you’re right. I meant polynomial not geometric. :P

Comment by codechicago277 4 hours ago

“Square of the lines of code”

Sounds exponential

Comment by dahart 4 hours ago

That’s quadratic, not exponential. 2^n != n^2

Comment by 4 hours ago

Comment by teiferer 2 hours ago

And that's why sw eng interviews often have some basic math sprinkled in.

Comment by Pannoniae 7 hours ago

it's not like microservices fare better, when you introduce them, you've traded a hard problem for a hard problem and distributed computing...

Comment by wg0 7 hours ago

Our industry has wasted hundreds of billions of dollars on this shit show called Microservices.

99.9% of shops need a monolith with same monolith having entry points for background workers and crons.

Comment by rglover 5 hours ago

I like LOEC: Lines of Effective Code.

Much easier to reason and make decisions if the bar is "yeah it exists, but is it effective relative to its intended purpose?" This weeds out buggy code as well as under performant code. If it's not effective (broken, too slow, etc), it either needs a refactor or thrown on the scrap pile.

Comment by elendilm 7 hours ago

Reducing attack surface is a lesson for everyone. Newcomers are impressed by massive piles of code.

Seasoned developers are unimpressed, or even disgusted, by the same massive piles of code.

Comment by someothherguyy 6 hours ago

i don't think LoC is the metric. sometimes fewer lines of code results in a larger attack surface through type coercion / widening, poor abstractions, hiding or stuffing behavior (modules that do everything), etc. to me, making code easy to understand, test, fuzz, and verify is more important. sometimes that requires more lines of code.

Comment by brazukadev 6 hours ago

LoC *IS* the metric. It is obviously not perfect tho but still the best one to compare software surface. Including to compare the same solution in different languages and platforms. The less code you need to manage, the less code you need to change and the less code you need to hold in your head to understand it (or in the LLM context nowadays).

Comment by pessimizer 3 hours ago

> Now what about those millions of lines of code? Wasn’t the agent swarm supposed to take care of it?

What's the joke? They're literally saying, every day, that this is true to a civilization endangering extent. They're making demands based on this, and politicians are taking up those demands.

And now they're paying bullshit $5K bug bounties for account-stealing exploits on their own platform. They should have paid more just the make the bug seem more grandiose; I don't know who let them get away with this - this is what happens when CEOs run their own PR I guess. It's basically an public announcement that they're total fakes.

Comment by 6thbit 6 hours ago

Appreciate the incremental write up building up the scope of the poc.

I like the chain of regular old school things used to achieve it like post message, JSONP, iframe, Img tags.

Comment by pllbnk 1 hour ago

It's exhilarating (for the lack of the knowledge of a better word) to see OpenAI and Anthropic starting getting hacked and getting a taste of their own medicine. Brings back hope that actual software engineering is not dead yet.

Comment by jwpapi 4 hours ago

I think there was another HN discussion about it re bounty value and as far as I remember the issue is not that big companies are greedy in that case, but rather that over time it’s strategically better to have lower bounties so less people are interested in it.

5 or 50k doesnt matter to them. And this bug in terms of severity is very high imho.

Comment by aprilthird2021 12 minutes ago

But couldn't they just turn around and sell this hackers for much more money?

Comment by htk 1 hour ago

5k makes me think the next guy is gonna sell his exploit in the black market instead.

Comment by Zeruxe 2 hours ago

5k is nothing for the amount of headache you just saved them..

Comment by atrokhymchuk 7 hours ago

if only they had some sort of cybersecurity state of the art thing...

Comment by 15o9o 9 hours ago

we are getting to the point of “why have passwords?” Right? At some point soon we have to move to the honor system of just please don’t login as me?

Comment by qup 6 hours ago

My latest project emails a magic link.

I'm trying not to have any important data to even lose, when I eventually get hacked.

We can all turn up our noses, like the other commenters in this thread, but every one of them is exposed. Negligence is a matter of degrees.

Comment by latexr 5 hours ago

> I'm trying not to have any important data to even lose

This is the way. Respect user privacy and keep as little data as possible, and not only do you become a less attractive target, if you are targeted the outcome won’t be so bad.

Comment by dataviz1000 7 hours ago

> please don’t login as me

Please don't drain my $6.5 billion in Dogecoin.

Comment by chamomeal 6 hours ago

Been sayin this for years. Everybody in the world world: just BE COOL. Solves like every internet problem at once.

Comment by 15o9o 5 hours ago

we all joke but spiritual communities have been saying this is the way for years. Like the law of one stuff.

Comment by jareklupinski 8 hours ago

> able to take over anyone's account simply by sending them a link

dont click links people

that'll be $500k for the security training pls

Comment by kro 7 hours ago

If they or their company use email "security" software that "scans" all links it's not necessarily the users fault / they don't in fact click. The mail is auto-confirmed the second it hits the inbox.

We've had to change our registration confirmation mails too recently to not confirm on GET only, but with another form - in hindsight it was stupid before but many services do that.

Comment by weird-eye-issue 5 hours ago

> We've had to change our registration confirmation mails too recently to not confirm on GET only, but with another form - in hindsight it was stupid before but many services do that.

This has been a thing since forever lol

Comment by dpark 5 hours ago

Security software fetching links will not trigger this behavior. It needs to be done in the context of the actual ChatGPT user so that a JavaScript payload can run.

If merely GET on the link was sufficient to trigger the behaviors, the adversary generating the link would just GET it themselves.

Comment by kro 4 hours ago

Yes, if it requires the user session (xss related), like the article, there is no problem.

I was replying more generally about the "don't click links" advice and cases of server generated confirmation-token links (not saying this was the case at OpenAI)

Comment by gokulravi992 7 hours ago

[flagged]

Comment by TobTobXX 7 hours ago

... says IT and then it sets Outlook to mangle link to abominations like [0]. "Check if the preview shows something different or suspicious."

[0]: https://che01.safelinks.protection.outlook.com/?url=https%3A...

Comment by Antipode 6 hours ago

I've worked at a company that did link mangling on everything except simulated phishing emails. The effect was that people were trained to trust the mangled links.

Comment by 5 hours ago

Comment by extraextra 5 hours ago

God I hate those

Comment by dist-epoch 7 hours ago

I wanted to check your website from your profile, but then I remembered your advice. Thanks!, dodged a potential bullet

Comment by bossyTeacher 8 hours ago

Also many emails from tech companies today:

- "sign in via one-time code."

- "Click here to see our latest update".

Comment by jareklupinski 7 hours ago

dont click links

250k refresher fee

Comment by pkthunder 6 hours ago

Click this link to be told not to click links.

Comment by atrokhymchuk 7 hours ago

hey, don't dump the market

Comment by kotaKat 7 hours ago

"Scan this QR code!"

Comment by 7 hours ago

Comment by Razengan 7 hours ago

Thanks! Here, click on this link to get paid

Comment by gib444 7 hours ago

[dead]

Comment by monster_truck 6 hours ago

only $5000 for this, lmao. It should be $50k out of pure shame. If they don't make these things hurt just a little they're never going to take following best practices seriously enough. There will be 9 more anyways.

Meanwhile the actual user of the account probably has to sign in using a yubikey because they get "CyBeRsEcRuItY aLeRtS" when they try to update node in their project to fix a crash and have to switch to daybreak blue to continue (or attempt to trick the normal models into doing it and risk getting autobanned)

Comment by j9feng 4 hours ago

Claude or Gemini didn’t find the vulnerability on ChatGPT?

Comment by Yieldz 3 hours ago

Sigh. With how good Openai are good in programming frontier agents, they still have weak security. Hmmn, i'm short of words.

Comment by nickphx 5 hours ago

why didnt the black box of bullshit company detect this? for a group that touts every inane 'discovery' with hyperbolic bullshit, they really fall short on delivering anything of actual value, just rehashed bullshit.

Comment by msarda_23 6 hours ago

[flagged]

Comment by marincoco1 4 hours ago

[flagged]

Comment by frank00001 5 hours ago

[flagged]

Comment by marwaneet 7 hours ago

Another classic OAuth implementation failure. Mismanaging the state parameter or leaking tokens via referer headers in redirects is Security 101. Wild to see this in a production environment of this scale.

Comment by brabel 6 hours ago

The post seems to be talking about a html injection via a postMessage call where the receiver didn’t check who sent the message, which is a well known vulnerability entry point. Did I miss where OAuth had anything to do with this??

Comment by steve1977 7 hours ago

Production scale is not production grade I guess...