CVE-2026-114049

Description

A flaw was found in vLLM. A remote attacker can compromise the integrity of responses generated for other users by submitting concurrent constrained generation requests. Due to improper state cleanup during batch reorganization, restriction rules defining permitted response tokens can persist in recycled memory slots. As a result, an attacker's token restrictions can be inadvertently enforced on unrelated client requests, improperly constraining their model outputs.

Common Vulnerability Scoring System (CVSS) Score Details

Info alert:Important note

CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).

The following CVSS metrics and score provided are preliminary and subject to review.

CVSS v3 Score Breakdown

Red HatNVDcve.org
Base Score3.7N/A3.7
Attack VectorNetworkN/ANetwork
Attack ComplexityHighN/AHigh
Privileges RequiredNoneN/ANone
User InteractionNoneN/ANone
ScopeUnchangedN/AUnchanged
ConfidentialityNoneN/ANone
Integrity ImpactLowN/ALow
Availability ImpactNoneN/ANone

Vector

Red Hat: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N

cve.org: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N

Understanding the Weakness (CWE)

Other,Confidentiality,Integrity

Technical Impact: Other; Read Application Data; Modify Application Data; DoS: Resource Consumption (Other)

It is possible to overflow the number of temporary files because directories typically have limits on the number of files allowed. This could create a denial of service problem.

Frequently Asked Questions

Want to get errata notifications? Sign up here.