HN

Need help?
<- Back
Using Claude to reduce the attack surface of code

Using Claude to reduce the attack surface of code

dnw

Comments (74)

  • petermora
    Recently I watched this presentation of a kernel developer about the "Mythos' 79 kernel vulnerabilities": https://youtu.be/NnV_cWeoo5Q?t=257He claims that most of these vulnerabilities are not an issue at all, or have been fixed earlier, etc. I can clearly see the improvement of the AI models, but based on this youtube video it's very plausible that these AI labs rush to announce a result without further understanding of the underlying problems. I wonder what's the quality here in this article.
  • tilemarch
    There is an unresolved issue where the offensive guys can use AI to attack a target and the defensive guys are being limited when they ask AI to audit their codebase.The workflow for a defender basically goes: Claude do a security audit on this codebase, use the harness / skills I built on how to do security audits.. pick the best suitable audit strategy, methods.. use the tooling and reporting structures.Claude refuses, GPT refuses. Grok, goes further, but refuses to make a working PoC.. a requirement because AI models make stuff up and without a PoC there is no proof. GLM-5.3 / Kimi to the rescue and completes the job the "smarter" models refused.So we as defenders are refused by the best models, on our own codebase
  • ethin
    I would believe Anthropic about how Claude reduces attack surfaces if they weren't simultaneously nannying everyone about how they supposedly don't want their models used for cybersecurity because... Reasons. And if you do want that access, you have to verify your identity, and do a bunch of other things, all of which goes against "reducing" the "attack surface". If they really gave a damn about cybersecurity, this cybersecurity filter wouldn't exist, period.
  • mentalgear
    There is really just one way this goes and its upwards to the peak: which means full formal verification programming languages, OS uni-kernels, small TCB and probably verified HW for the most sensitive cases. Everything else will soon be hackable via 'brute compute' because economy of scale and accessibility of open weight models.
  • jph
    I'm doing this attack surface tactic with Vix IDE, a terminal text editor that helps novices get comfortable with vi, emacs, git, jj, sql, commands, and more.The prompt I used was "Goal: rework to reduce the attack surface. Process: move features into feature-flag Rust crates. Output: build a minimal version. Questions: Ask me anything."https://github.com/vixide/vixThis past weekend, Claude Fable/Opus/Sonnet together successfully refactored the whole Vix IDE codebase into many separate Rust crates and Cargo features.This refactor enables a security-oriented user to pick and choose, and also makes it easier for a security auditor to look at one capability at a time.If you're curious you can see the commit messages by Claude Sonnet. IMHO they're reasonably good.
  • lptome
    I'd really expect a company like Anthropic to proof-read their posts. I found at least 4 typos in this.
  • messe
    If only Claude didn't constantly drop to less capable models whenever it encountered anything vaguely cybersecurity related (despite being part of the Anthropic Cyber Verification Program and having Mythos access, albeit limited).We're strongly pushing for a move to a mix of Codex and open models at my workplace because of Anthropic's ridiculous nanny-ing.
  • StilesCrisis
    > leaving a features behavior undefinedMissing an apostrophe? A human wrote this! Love to see it.
  • owebmaster
    The irony of a company using Nextjs for a chat app and React for a terminal UI talking about reducing attack surface.
  • Zambyte
    > Team: Frontier Red TeamThis sounds so arrogant, lol. I know it actually means that they red team the frontier AI models (which is a reasonable claim), but it looks like they are claiming to be the best red team in the world
  • Marcom07
    Nice article! Thanks for sharing.
  • syngrog66
    base rule: dont use Claude. never run it or allow it to be installed anywhere
  • vasco
    These guys are now the biggest slowdown to fixing issues with their bullshit cyber detection. They drop a model, let the model find security issues in your code, then when you want to fix them you need to play a game of charades so it doesn't realize it's creating a validation and then a fix for the issue because you might be hacking yourself. Meanwhile attackers are using some ablated deepseek or what have you.