Claude wrote a root exploit for a Linux kernel bug. Ubuntu's LTS kernels still aren't fixed.
Hey 👋
Two stories this week. The first is Anthropic saying Claude wrote a working root exploit for a Linux kernel bug, and the distribution patches that still haven’t shipped. The second is a correction to #33.
In #33 I wrote that LiteLLM traced its break-in to GitHub tokens in its own gateway logs. That was LiteLLM’s working theory on 21 October. Its root-cause analysis two days later contradicts it, so I’ve put the corrected chain below.
My take, in one line: the attacker’s skill was not the scarce thing in either story. A patch that hadn’t shipped and a key nobody revoked were.
This week in AI security
Anthropic: Claude wrote a root exploit for a Linux kernel bug
On 27 October, Anthropic’s Frontier Red Team published results from using Claude to find vulnerabilities. The headline claim: “After initial prompting, Claude wrote an exploit that allows a remote attacker to send packets to Linux servers with a multipath TCP listener to run arbitrary commands as root.” The bug is CVE-2026-98432, which Anthropic says “was patched upstream and backported to all maintained stable kernel branches.” In its proof of concept, “it takes 48 minutes to leak a kernel pointer and another five minutes to reach the shell command execution.” No exploit code was released.
The kernel CVE team’s record adds what Anthropic’s post leaves out. It is a race in the TCP handshake that causes a use-after-free in ip_options_build(), scored CVSS 9.8, introduced in kernel 4.4. The fixes landed in 5.10.272, 5.15.223, 6.1.190, 6.6.159, 6.12.113, 6.18.56, 7.2.10 and 7.3.
Two things in the record are worth reading closely:
- The CVE text doesn’t mention multipath TCP. The MPTCP listener is the path Anthropic’s exploit used. The Hacker News makes the same point. Whether the bug is reachable without MPTCP isn’t something I could settle from the record.
- Distribution status lags. Ubuntu published the CVE on 15 October. As of 7 November, only 26.10 shows a fix (7.3.0-10.10). 26.04, 24.04, 22.04 and 20.04 are all marked “work in progress,” 23 days after publication. The Hacker News reported on 29 October that Red Hat and Amazon rated the bug lower than the kernel team’s 9.8, and that Debian and Oracle had shipped fixes. I only read Ubuntu’s page directly.
I can’t tell you how much of the 53 minutes is Claude and how much is Anthropic’s setup. The post says “after initial prompting,” which leaves room for a lot of human steering. The part I can verify is the timeline: a public 9.8 with a root exploit demonstrated, and the supported Ubuntu LTS kernels still unfixed three weeks after the CVE.
So what: the gap between “CVE published” and “fix on your hosts” used to be the defender’s slack. A model that can write the exploit shortens the attacker’s side of that gap, and the distribution’s side didn’t move.
Do this: check your distribution’s tracker for CVE-2026-98432, not your kernel version, since vendors backport fixes. For hosts that are internet-facing and unfixed, check whether you need MPTCP (
sysctl net.mptcp.enabled). Turning it off blocks the path Anthropic demonstrated. My inference is that it is not a fix for the bug itself, so keep patching on the list.
Correction: LiteLLM’s first token did not come from the logs
LiteLLM’s attack-chain write-up (23 October) supersedes the 21 October incident post that #33 relied on. In its words: “Our first post suspected the tokens were taken from the logs of an internal LiteLLM deployment. The request logs show the first token came from a different service.” The chain it now describes:
- 27 May. A config file containing an administrative key to LiteLLM’s internal Agent Platform was committed to the public
LiteLLM-Labs/lite-harnessrepository. A follow-up commit deleted the file, but the original commit stayed in public history until 22 October. - Never revoked. “Because of human error, nobody followed through on revoking the administrative key,” so it “was still valid more than four months later.”
- 10 October. The attacker used the key to call the Agent Platform API. One request returned the GitHub CLI token of LiteLLM’s organization owner. LiteLLM’s note on that token type: “GitHub CLI tokens are not scoped, are post-2fa, and not subject to GitHub’s ‘super-user’ 2fa reauth flows.”
- 10 and 12 October. Throwaway CI workflows posted secrets to
webhook.site, which yielded two more maintainer tokens. The attacker used separate tokens “to evade detection by way of noisy audit logs.” - 21 October. The release of 1.107.0 described in #33, using three different people’s tokens.
The Claude Code claim from #33 (that Claude Code embeds a user’s GitHub CLI token in a response body) was in LiteLLM’s first post. The new write-up doesn’t mention it, and I still found no statement from Anthropic. I’d treat it as unconfirmed.
One detail matters if you verify LiteLLM images: LiteLLM believes the private half of its old cosign key was exposed and rotated it on 23 October. The bad v1.107.0 images “also carry a valid signature from the previous key,” so a valid old-key signature proves nothing about an image published after 21 October.
So what: the compromise needed no log mining and no zero-day. It needed one admin key that outlived the file it was committed in, and one CLI token with the full rights of its owner. Deleting a secret from the latest commit does nothing for the key.
Do this: scan the full history of your public repos for committed secrets, not just the current tree, and revoke anything you find instead of deleting it. Then list the GitHub CLI tokens your org owners and maintainers hold. They are unscoped, so for anything automated, use a fine-grained token or an app with the narrowest scope that works.
What I’m writing
The IETF agent-identity piece I mentioned in #33 is still in the queue. It covers what the IETF has actually finished for agent identity and what is still a draft. The short version hasn’t changed: the finished parts are general OAuth, and the agent-specific parts are drafts.
Tooling worth knowing
- LiteLLM’s attack-chain post has the full timestamped timeline, the request that returned the token, and the cosign fingerprint to verify against. post →
- Agent Security Scorecard: my free self-assessment against the OWASP Agentic Top 10. About 12 minutes, no login. Score your agents →
- AI Agent Pre-Deployment Security Checklist: 25 yes/no controls to clear before an agent with tool access goes to production. Get the checklist →
One thing to check this week
Spend twenty minutes on keys that outlived their reason to exist.
- Scan history, not the tree. Run a secret scanner over the full git history of every public repo your org owns. The LiteLLM key was deleted from the file and still worked.
- Revoke, then ask what it could reach. For anything you find, revoke first. Then ask what an attacker holding it could read, because LiteLLM’s key could read an API that returned a token.
- List unscoped tokens. Find the CLI and OAuth tokens held by org owners and release maintainers. If one can approve a production release, it shouldn’t also be a token a service can hand out.
What I’m watching
→ Anthropic on the token-in-response-body claim. Still no statement, and the root-cause analysis is now silent on it too.
→ Distribution kernels for CVE-2026-98432. Whether Ubuntu’s 26.04, 24.04 and 22.04 LTS kernels move from “work in progress” to a fixed package, and whether anyone shows the bug is reachable without MPTCP.
→ Microsoft Ignite, 17 November. Whether “controls outside the agent’s reach” ships as a product, and on which licence.
If you find a committed key that’s older than the repo’s last release, reply and tell me how long it had been there. I read everything.
Cheers, Amine
If a colleague maintains an open-source project with a release pipeline, forward this to them.
Sources
- The attack chain behind the v1.107.0 LiteLLM release, LiteLLM, 23 October 2026
- Security incident: LiteLLM v1.107.0, LiteLLM, 21 October 2026 (updated 23 and 30 October)
- Discovering vulnerabilities with Claude, Anthropic Frontier Red Team, 27 October 2026
- CVE-2026-98432 record, Linux kernel CVE team
- CVE-2026-98432, Ubuntu Security, page last updated 7 November 2026
- Linux kernel TCP flaw with 9.8 CVSS score affects Ubuntu, Red Hat and other distributions, The Hacker News, 29 October 2026