Hacker News Viewer

Claude Wrote a Full FreeBSD Remote Kernel RCE with Root Shell (CVE-2026-4747)

by ishqdehlvi on 4/1/2026, 5:21:48 AM

https://github.com/califio/publications/blob/main/MADBugs/CVE-2026-4747/write-up.md

Comments

by: magicalhippo

Key point is that Claude did not <i>find</i> the bug it exploits. It was given the CVE writeup[1] and was asked to write a program that could exploit the bug.<p>That said, given how things are I wouldn&#x27;t be surprised if you could let Claude or similar have a go at the source code of the kernel or core services, armed with some VMs for the try-fail iteration, and get it pumping out CVEs.<p>If not now, then surely not in a too distant future.<p>[1]: <a href="https:&#x2F;&#x2F;www.freebsd.org&#x2F;security&#x2F;advisories&#x2F;FreeBSD-SA-26:08.rpcsec_gss.asc" rel="nofollow">https:&#x2F;&#x2F;www.freebsd.org&#x2F;security&#x2F;advisories&#x2F;FreeBSD-SA-26:08...</a>

4/1/2026, 9:59:15 AM


by: ptx

&gt; <i>It&#x27;s worth noting that FreeBSD made this easier than it would be on a modern Linux kernel: FreeBSD 14.x has no KASLR (kernel addresses are fixed and predictable) and no stack canaries for integer arrays (the overflowed buffer is int32_t[]).</i><p>What about FreeBSD 15.x then? I didn&#x27;t see anything in the release notes or the mitigations(7) man page about KASLR. Is it being worked on?<p>NetBSD apparently has it: <a href="https:&#x2F;&#x2F;wiki.netbsd.org&#x2F;security&#x2F;kaslr&#x2F;" rel="nofollow">https:&#x2F;&#x2F;wiki.netbsd.org&#x2F;security&#x2F;kaslr&#x2F;</a>

4/1/2026, 10:35:52 AM


by: panstromek

The talk &quot;Black-Hat LLMs&quot; just came out a few days ago:<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=1sd26pWhfmg" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=1sd26pWhfmg</a><p>Looks like LLMs are getting good at finding and exploiting these.

4/1/2026, 10:07:45 AM


by: m132

Appreciate the full prompt history

4/1/2026, 10:03:59 AM


by: PunchyHamster

I&#x27;m just gonna assume it was asked to fix some bug and it wrote exploit instead

4/1/2026, 9:53:39 AM


by: fragmede

<a href="https:&#x2F;&#x2F;github.com&#x2F;califio&#x2F;publications&#x2F;tree&#x2F;main&#x2F;MADBugs&#x2F;CVE-2026-4747" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;califio&#x2F;publications&#x2F;tree&#x2F;main&#x2F;MADBugs&#x2F;CV...</a> would have been a better link

4/1/2026, 10:02:15 AM


by: Adam_cipher

[dead]

4/1/2026, 11:42:27 AM


by: rithdmc

Running into a meeting, so won&#x27;t be able to review this for a while, but exciting. I wonder how much it cost in tokens, and what the prompt&#x2F;validator&#x2F;iteration loop looked like.

4/1/2026, 9:59:23 AM