Hacker News 讨论 ChatGPT Desktop 将 SSH agent 转发到远程机器的安全隐患

Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

ChatGPT Desktop forwards your SSH agent to remote machines 36 points by DenGorbachev3 hours ago | hide | past | favorite | 9 comments The agent running on a remote machine can authenticate using your local SSH credentials. That means it can push to your private repos on GitHub, for example. Proof: https://github.com/openai/codex/pull/28131#discussion_r3410013180 help recsv-heredoc1 hour ago | next[–] It's amazing how often product decisions head this way for the purposes of 'removing friction'. In security, friction is a GOOD thing. You want to have some ceremony to do things. It's pretty much inevitable that people will give up control for convenience. Look at Artifacts for example. reply littlecranky672 hours ago | prev | next[–] I'd suggest to use ssh keys inside the secure enclave on macOS that require your fingerprint for every new session [0]. That way agents cannot initiate anything, and you will always be aware when a new ssh connection is being made. [0]: https://gist.github.com/arianvp/5f59f1783e3eaf1a2d4cd8e952bb... reply bradfa58 minutes ago | parent | next[–] Or in a Yubikey and set the touch-required mechanism (light in the key will blink when it needs a touch to continue the auth). reply itissid53 minutes ago | parent | prev | next[–] I've been using secretive on the mac for exactly this. reply m0001 hour ago | prev | next[–] At this point, should cases like this even be news? Isn't that a fundamental security design issue? Local agent security guardrails appear to always be built around blacklists, which will always be unreliable and leaky. It is left as an exercise to the user to properly sandbox them. There may be some limited form of whitelisting, but often it is just a facade, as it is very coarse-grained. So, with tools with very broad capabilities (ssh, kubectl, gcloud, etc) you end up with the agent performing unwanted actions. reply pierremangin1 hour ago | prev | next[–] I'm unfortunately not a security expert, but I am a big fan of desktop harnesses. These BYOK projects pretend to be build with security in mind. Should we believe them? - Openworker (https://github.com/andrewyng/openworker) - PraisonAI (https://github.com/MervinPraison/PraisonAI) reply Betelbuddy1 hour ago | prev | next[–] They might have solved coding but they did not solve common sense. reply m00056 minutes ago | parent | next[–] I think the agent "eagerness" tuning leaves much to be desired. They are very zealous when performing random tasks, resorting to all kinds of dodgy actions just to get it done. Then you ask them to help you with the security of your own repo, the one you've been adding code to day after day for months, and they go full Gandalf on you: "Thou shall not pass!" reply spwa41 hour ago | prev[–] Of course it does. That's what the codex <> chat merge is actually doing. But codex <> chat merge is what they're giving as the "real reason" for what actually is raising prices (a LOT, I might add) for all the subscriptions. Nobody wants it (certainly not applied globally to everything like it is), but they're still going to do it. I even know someone who works at OpenAI and there's apparently a few people trying to fight it at least internally. Given Sam Altman's speech about how he wants OpenAI pricing to work, I don't think this can be stopped. Btw: that is that you type something into ChatGPT and instead of subscription or per-token cost or anything like that, as soon as you type something in, anything, the way he sees it, ChatGPT would give you a cost for that specific answer and you'd agree or not. I just feel like this guy is an even worse example of not seeing the viewpoint of a normal (you know non-millionaire) person than even Google's leadership. Can I just say "I think Google is going to win from Altman", you know, despite OpenAI having the far superior technology. Because if there's one guy in the whole world that can destroy the advantages of OpenAI's engineering accomplishments for everyone else, it's this guy ... reply Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: