[CamperBob2]

It's hard enough to report issues to OpenAI. Not surprising that information coming out of the company is equally constrained.

Right now my ChatGPT4 history is full of chats I didn't create, on subjects ranging from corporate governance to Roblox scripting to somebody's math homework. It will be only a matter of time before this bug causes them to leak sensitive personal data. I spent 10 minutes looking for a way to report it, but they have successfully insulated themselves from any contact with their (paying) customers.

Pretty annoying, and not something you expect from a supposedly security-savvy company... although that expectation is certainly changing.

[upwardbound]

Would you be open to collaborating to investigate whether we can further widen this bugged behavior, demonstrate that it's serious, and get it fixed? You could reach me at [e-mail]

It sounds like the bug affecting your account is uncommon, making your account special, and as an AI security researcher I can help investigate the extent of the issue and I have contacts that can help call attention to it. Thank you for discovering this and trying to escalate this.

[righthand]

Serious question: What gave you the impression the company is security savvy?

[moralestapia]

Not OP but probably all their marketing bs about AI safety and how they're saving the world by not destroying it (th-thanks ...).

They can't even do basic auth properly so ...

[gunapologist99]

It's good to see that we are safely protected from the other side of the political aisle.

[talldayo]

With business partners like these, who needs competitors?

[paulryanrogers]

Don't follow. Can you explain the political connection?

[righthand]

I guessed that but also AI safety doesn’t seem like a security promise to me so I thought I’d clarify.

[chillingeffect]

btw fwiw my passwd in chatgpt is all lowercase lol

[Algemarin]

> It's hard enough to report issues to OpenAI.

Not at all. OpenAI follows basic accepted standards for security reporting. This is like complaining that you can't find if a website doesn't want specific directories crawled because you don't know about the existence of a robots.txt.

Specifically, OpenAI has a security.txt [0], which is:

> an accepted standard for website security information that allows security researchers to report security vulnerabilities easily [1]

Whenever attempting to find where to report a security issue, the easiest thing to do is always check if the website has a security.txt file.

[0] https://openai.com/security.txt

[1] https://en.wikipedia.org/wiki/Security.txt

Here's their security.txt:

  -----BEGIN PGP SIGNED MESSAGE-----
  Hash: SHA512
  
  #
  #           .d88888b.             
  #         .8P"     "9bd888b.      
  #        .8P     .d8P"   `"988.   
  #     .8888   .d8P"    ,     98.  
  #   .8P" 88   8"    .d98b.    88  
  #  .8P   88   8 .d8P"   "98b. 88  
  #  88    88   8P"  `"8b.    "98.  
  #  88.   88   8       8"8b.    88 
  #   88    "98.8       8   88   "88
  #    `8b.    "98.,  .d8   88    88
  #    88 "98b.   .d8P" 8   88   d8"
  #    88    "98bP"    .8   88 .d8" 
  #    "8b     `    .d8P"   8888"   
  #     "88b.,   .d8P"     d8"      
  #       "9888P98b.     .d8"       
  #               "988888P"         
  #
  Contact: https://bugcrowd.com/openai
  Acknowledgments: https://bugcrowd.com/openai/hall-of-fame
  Policy: https://openai.com/policies/coordinated-vulnerability-disclosure-policy
  Hiring: https://openai.com/careers/search?c=security
  Canonical: https://openai.com/.well-known/security.txt
  Encryption: https://cdn.openai.com/security/disclosure.asc.pub
  
  # You may also email us directly.
  Contact: mailto:[e-mail]
  -----BEGIN PGP SIGNATURE-----
  
  iHUEARYKAB0WIQQ5fYPd6Hi19rZDZ+kKj1HZ7OnINQUCZbiKWgAKCRAKj1HZ7OnI
  NS9+AQCTx4vlrCp+Urd1fa/lAQ3dcV8VNHOxA4JnxD0TH2nxwQEAuqoxenxPZWeD
  +IsSikn4em/LEheOeAakGDzZedcu1QE=
  =rMRk
  -----END PGP SIGNATURE-----

[upwardbound]

The email address they have listed there is defunct, and they haven't bothered to update this security.txt page. When you try emailing [e-mail], you get an auto-reply saying:

    Hello and thank you for reaching out to OpenAI. Our vulnerability disclosure program has migrated to OpenAI's bug bounty program, and this mailbox is no longer monitored. Please use the "submit report" functionality available through our bug bounty platform to inform us of security concerns, or reach out to [e-mail] for any non-security-related inquiries.

    Thank you for your help in securing OpenAI!

    Bug Bounty Program: https://bugcrowd.com/openai

[CamperBob2]

LOL.

... that was a joke, right? So only people who have heard of the security.txt convention are expected to find this information easily when they need to report a bug?

[ballenf]

This came up with my first search "openai security": https://trust.openai.com

At the bottom is a link to report an issue. Seems like there are multiple ways to report issues. And they come with the potential for bug bounties.

And so many companies don't follow the security.txt standard that it puts OpenAI well ahead of most companies.

[CamperBob2]

This came up with my first search "openai security": https://trust.openai.com At the bottom is a link to report an issue.

Did you click the link? What happened when you did?

[skywhopper]

Who has claimed OpenAI is security-savvy?

[boulos]

Huh? I just went to OpenAI.com and there is a little "Security" link in the bottom pile that points to https://openai.com/security-and-privacy/ .

Under "Reporting security issues" it points you to a bug bounty page: https://bugcrowd.com/openai with a bunch of explanations.

I'm guessing if you also just send an email to [e-mail] it'll go to someone. Using Bugcrowd just seems like a nice way to also run a bug bounty as part of their normal intake.

[upwardbound]

OpenAI seems to have, unfortunately, outsourced the triaging of bug bounty reports to people who don't seem to understand security well enough to recognize issues. As an example, I've been trying to get OpenAI to fix the fact that "eval()" is used incorrectly in one of their Cookbooks in a place where the correct function would be "json.loads()".

https://cookbook.openai.com/examples/how_to_call_functions_w...

https://news.ycombinator.com/item?id=40474451#40474452

The bug bounty report was closed with a message saying:

    Upon reviewing your report and consulting with the OpenAI team, we have determined that this feature is operating as intended. This means it does not constitute a valid sandbox escape. The Code Interpreter environment is securely sandboxed to support code writing and execution, including shell operations. Any code execution within this environment falls outside the scope of our program ... As you have not demonstrated a valid sandbox escape or RCE, we're closing this submission as Not Applicable.

This shows a fundamental misunderstanding of basic coding, as the eval() I pointed them to is completely unrelated to the Code Interpreter environment. So, the report is incorrectly considered "Not Applicable", without any real further ways to try to get them to fix it. I tried contacting the Cookbook authors directly, but never heard back.

[CamperBob2]

I saw that.

I can't be arsed to create an account on a third party 'bug bounty' site, or to waste time guessing email addresses, or to download a security.txt file I've never heard of. Sorry. Their loss, not mine. If they make it hard for me to help them, they can't be too surprised when I give up trying.