Cases › security breach › LR-2026-0292
Anthropic Claude model develops working Linux kernel MPTCP root exploit (CVE-2026-98432)
Preliminary Why: 1 report: BleepingComputer · subject to change · 1 independent report
Severity minor: The exploit was demonstrated in a research setting against a single Linux server running an MPTCP listener, with no confirmed in-the-wild exploitation.
Earliest source we hold 2026-10-30 · Captured by AI Risk Wire 2026-10-31 03:27 UTC
Anthropic researchers reported that an unreleased Claude AI model developed an exploit for CVE-2026-98432, a use-after-free race condition in the Linux kernel's IPv4 TCP code affecting kernels back to 4.4.
Risks this incident falls under
| Risk | Role | NIST AI 600-1 | Incidents | Last 6 quarters |
|---|---|---|---|---|
| AI used to run a cyber attack | Primary | Information Security | 33 | |
| AI system attacked or breached | Also | Information Security | 1 |
Sorted by rule from the case's fields; not yet read from the sources.
Control failure chain
L1 · ModelProvider not namedModel provider
Sources not yet read for controls.
Model version not linked to a model card.
9 more for this risk at this layer
L2 · HarnessHarness not namedAgent framework vendor
Sources not yet read for controls.
L3 · ApplicationDeployer not namedDeployer
Sources not yet read for controls.
L4 · Infrastructure / targetOrganisation hitOrganisation hit
Sources not yet read for controls.
6 more for this risk at this layer
HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target
The same controls in other incidents of this risk
| Control | Layer | Here | Held elsewhere | Did not hold elsewhere |
|---|---|---|---|---|
| Content safety classifiers | L1 Model | Not read yet | – | – |
| Safety training and refusal | L1 Model | Not read yet | – | 1 |
| Cyber and weapons safeguards | L1 Model | Not read yet | – | – |
| Dangerous-capability testing before release | L1 Model | Not read yet | – | – |
| Outside red-teaming | L1 Model | Not read yet | – | – |
| Staged or restricted release | L1 Model | Not read yet | – | – |
| Abuse monitoring and account enforcement | L1 Model | Not read yet | – | – |
| Reasoning monitoring | L1 Model | Not read yet | – | 1 |
| Safeguards kept on in testing | L1 Model | Not read yet | – | – |
| Known flaws patched | L4 Infrastructure / target | Not read yet | – | – |
| Multi-factor sign-in and password policy | L4 Infrastructure / target | Not read yet | – | – |
| Network segmentation | L4 Infrastructure / target | Not read yet | – | – |
| Intrusion and endpoint detection | L4 Infrastructure / target | Not read yet | – | – |
| Backups and recovery | L4 Infrastructure / target | Not read yet | – | – |
| Phishing and fraud filters | L4 Infrastructure / target | Not read yet | – | – |
Remediation
Fix reported
“The vulnerability was fixed in the upstream Linux kernel and backported to maintained kernel branches.”
No later incident for Anthropic under this risk on record.
Risk grouping: Not yet classified
No source we hold states: who caused it, intended or not, before or after release, the ai's part.
The story
No source states: how it was caught, when it was found, how many records were exposed, the direct loss, a count of the other parties affected, any court case, the cause, what set it off.
Others like this
Anthropic Claude models gained unauthorized access to real third-party systems during evaluations 2026-10-22
Show every field, with its source and grade
The AI system
What happened
Impact
Context
LR-2026-0292 · version 2 · published 2026-10-31 after automatic checks; not yet checked field by field by a person · changes to this case · JSON