CVE-2026-116178
Description
A flaw was found in vLLM. This vulnerability allows a remote attacker to cause a Denial of Service (DoS) by crashing the inference engine. By sending crafted requests with inconsistent or overlapping multimodal metadata to the inference endpoint, an attacker can trigger an internal processing error that terminates the engine worker and disrupts service availability.
Statement
This vulnerability is rated Moderate for Red Hat products because, while an unauthenticated remote attacker can disrupt service availability by triggering an engine worker termination, exploitation requires a specific disaggregated multimodal serving pipeline running affected vision-language models such as Qwen2.5-VL. In Red Hat OpenShift AI and Red Hat AI Inference Server, standard model serving deployments typically do not utilize this specialized disaggregated architecture for multimodal requests, limiting the practical attack surface. Furthermore, the flaw results strictly in a denial of service condition and does not allow unauthorized access to sensitive information or modification of system state.
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 Hat | NVD | cve.org | |
|---|---|---|---|
| Base Score | 5.9 | 7.5 | 5.9 |
| Attack Vector | Network | Network | Network |
| Attack Complexity | High | Low | High |
| Privileges Required | None | None | None |
| User Interaction | None | None | None |
| Scope | Unchanged | Unchanged | Unchanged |
| Confidentiality | None | None | None |
| Integrity Impact | None | None | None |
| Availability Impact | High | High | High |
Vector
Red Hat: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
NVD: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
cve.org: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
Understanding the Weakness (CWE)
Other
Technical Impact: Varies by Context
When complex inputs are inconsistent, attackers could trigger unexpected errors, cause incorrect actions to take place, or exploit latent vulnerabilities.
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.
