Skip to main content
No exploitation reportedFix availableAwaiting NVD analysis

CVE-2026-68903

LLMKube: Arbitrary Host File Read via Model.spec.source hostPath Injection

No exploitation reported by the sources we read.

  • Published2026-11-18
  • Fixed in0.9.0
  • WeaknessCWE-22

Am I affected?

With a domain, we read the version its public headers and pages expose. A distribution build can carry the fix under an older number.

Description

LLMKube is a Kubernetes operator for self-hosted large language model inference across heterogeneous hardware. Prior to 0.9.0, the ModelReconciler accepts arbitrary absolute paths and file:// URIs in Model.spec.source without restricting them to approved roots. A namespace user who can create or update Model and InferenceService resources can cause copyLocalModel to open an attacker-selected file in the controller pod or cause a HostPathVolumeSource to mount an attacker-selected node file when modelCache.enabled is enabled, which is the default. The selected file is copied into model storage and can expose controller service-account credentials or other node secrets outside the attacker's namespace. This issue is fixed in version 0.9.0.

Timeline

dates in UTC
  1. 2026-11-1820:02CVE publishedCNA

Versions per branch

OSV
defilantech/llmkube
BranchAffectedFixed in
0.9< 0.9.00.9.0

as publishedRanges as NVD and OSV publish them; a distribution’s build can be fixed under an older number.

Products declared by the CNA1 product

As GitHub_M, the CNA that assigned this CVE, declared them in the CVE record; versions as written.

  • defilantech LLMKube
    Affected
    • = < 0.9.0no fix stated

Source: the CNA record (CVE Program), © The MITRE Corporation,CVE Terms of UseCVE recordupdated 2026-11-18

Fix

  1. Update defilantech/llmkube to 0.9.0

Detection

Nuclei template
none so far
ProjectDiscovery
Exploit-DB
no entry
Exploit-DB
Metasploit modules
none listed
Metasploit Framework

Sources

  • CNACVSS 3.17.72026-11-18
  • CNAweakness (CWE)CWE-222026-11-18
  • NVDweakness (CWE)CWE-22read 2026-11-18
  • OSVaffected packages—
  • GitHub AdvisoriesadvisoryHIGH2026-11-18

Identifiers

Technical details

CVSS v3 Vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
Published
2026-11-18
Last Modified
2026-11-18
NVD status
Received
GitHub Advisory
GHSA-jw3m-8q7m-f35r

Frequently asked questions

What is CVE-2026-68903?

LLMKube is a Kubernetes operator for self-hosted large language model inference across heterogeneous hardware. Prior to 0.9.0, the ModelReconciler accepts arbitrary absolute paths and file:// URIs in Model.spec.source without restricting them to approved roots. A namespace user who can create or update Model and InferenceService resources can cause copyLocalModel to open an attacker-selected file in the controller pod or cause a HostPathVolumeSource to mount an attacker-selected node file when modelCache.enabled is enabled, which is the default. The selected file is copied into model storage and can expose controller service-account credentials or other node secrets outside the attacker's namespace. This issue is fixed in version 0.9.0.

Is CVE-2026-68903 actively exploited?

Active exploitation of CVE-2026-68903 has not been confirmed.

What is the CVSS score for CVE-2026-68903?

CVE-2026-68903 has a CVSS v3 base score of 7.7 (HIGH severity), with vector string CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N.

Running defilantech/llmkube? Hear about its next vulnerability

Surveillance reads the versions in your stack — a domain, a lockfile or a list — checks each CVE against the ranges its sources publish, and alerts you when one you run is exploited or enters CISA KEV. A version it cannot read stays « version not verified ».

No credit card required · No monthly cap on website lookups · 250 API requests/month

Sources for this record