CVE-2026-126394
Description
A flaw was found in vLLM. A remote, unauthenticated attacker can cause a Denial of Service (DoS) by submitting requests with an excessively large video frame count parameter to the application programming interface (API) server. Because the video processing backend fails to enforce an upper bound on frame allocations, processing the request exhausts system memory and processor resources, causing the server process to crash.
Statement
This vulnerability is rated as having Moderate impact because remote, unauthenticated attackers can cause a denial of service through process crashes or CPU starvation, but cannot compromise confidentiality or integrity. In Red Hat environments deploying vLLM serving engines for multimodal workloads, requests can invoke the vulnerable video processing backend even when models do not select it by default. The blast radius is limited to the availability of the inference service instance, with container orchestrators typically restarting crashed pods.
Mitigation
Restrict network access to the vLLM service to trusted internal networks and authenticated clients only. If vLLM is deployed behind an API gateway, ingress controller, or reverse proxy, configure request validation to drop or sanitize incoming multimodal requests that specify an unapproved video_backend parameter or excessive frame counts.
To limit network exposure on a host using firewalld, restrict access to the API port (for example, port 8000) to trusted sources:
# firewall-cmd --zone=trusted --add-source=<TRUSTED_IP_RANGE> --permanent
# firewall-cmd --zone=public --remove-port=8000/tcp --permanent
# firewall-cmd --reload
Warning: Modifying and reloading the firewall configuration will immediately terminate access for disallowed addresses and can briefly disrupt active connections. Restricting network access prevents untrusted clients from sending crafted multimodal payloads to the endpoint.
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 | 5.3 | N/A | 5.3 |
| Attack Vector | Network | N/A | Network |
| Attack Complexity | Low | N/A | Low |
| Privileges Required | None | N/A | None |
| User Interaction | None | N/A | None |
| Scope | Unchanged | N/A | Unchanged |
| Confidentiality | None | N/A | None |
| Integrity Impact | None | N/A | None |
| Availability Impact | Low | N/A | Low |
Vector
Red Hat: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
cve.org: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
Understanding the Weakness (CWE)
Availability
Technical Impact: DoS: Resource Consumption (CPU); DoS: Resource Consumption (Memory); DoS: Resource Consumption (Other)
When allocating resources without limits, an attacker could prevent other systems, applications, or processes from accessing the same type of resource. It can be easy for an attacker to consume many resources by rapidly making many requests or causing larger resources to be used than is needed.
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.