CVE-2026-68903
Published:November 18, 2026
Updated:November 19, 2026
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.
Affected Packages
https://github.com/defilantech/LLMKube.git (GITHUB):
Affected version(s) >=v0.4.10 <v0.9.0Fix Suggestion:
Update to version v0.9.0github.com/defilantech/llmkube (GO):
Affected version(s) >=v0.4.10 <v0.9.0Fix Suggestion:
Update to version v0.9.0Related Resources (7)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.3
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
LOW
User Interaction
NONE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
NONE
Vulnerable System Availability
NONE
Subsequent System Confidentiality
HIGH
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
7.7
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
NONE
Scope
CHANGED
Confidentiality
HIGH
Integrity
NONE
Availability
NONE
Weakness Type (CWE)
Improper Limitation of a Pathname to a Restricted Directory
EPSS
Base Score:
0.50