CVE-2026-100650

[CVE catalog]

Severity

High · CVSS 7.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Published

Sep 13, 2026, 10:00:00 PM UTC

Updated

Sep 26, 2026, 2:16:47 PM UTC

Source

[NVD] · [CVE record]

EPSS

0.81% · Oct 25, 2026

A flaw was found in vLLM. The system fully downloads and decodes remote or embedded media files before enforcing configured size and quantity restrictions. A remote attacker can exploit this vulnerability by submitting requests containing excessively large or numerous media payloads, forcing the server to consume excessive memory and network bandwidth. This resource exhaustion can lead to a Denial of Service (DoS), rendering the service unresponsive or causing it to crash. vllm: vLLM: Denial of Service via unbounded media ingestion This vulnerability is rated as an Important severity flaw because it can be triggered remotely without authentication to crash the inference service via resource exhaustion, completely disrupting model serving availability. In Red Hat Enterprise Linux AI and OpenShift AI environments, deployments hosting vLLM handle multi-modal requests or tokenization operations where input acquisition occurs prior to applying payload size constraints. Because excessive system memory and outbound bandwidth can be consumed before request rejection occurs, an adversary can exhaust container resources, though the flaw does not allow code execution or data exposure. The CVSS score(s) listed for this vulnerability do not reflect the associated product's status, and are included for informational purposes to better understand the severity of this vulnerability.