CVE-2026-105760

[CVE catalog]

Severity

Medium · CVSS 5.3CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L

Published

Oct 5, 2026, 10:00:00 PM UTC

Updated

Oct 5, 2026, 11:17:02 PM UTC

Source

[NVD] · [CVE record]

EPSS

0.30% · Oct 25, 2026

A flaw was found in vLLM. A remote attacker can trigger a Denial of Service (DoS) by submitting a request with excessively large frame rate and frame count options for the GLMGA video backend. Because the application constructs intermediate frame index lists without proper upper bounds, processing these requests consumes disproportionate CPU and memory resources, potentially causing service degradation or unresponsiveness. vllm: vllm: Denial of Service via excessive resource consumption in GLMGA video backend A moderate-impact denial of service flaw was found in the vLLM inference and serving engine, which Red Hat ships in the Red Hat AI Inference Server and Red Hat OpenShift AI (RHOAI) container images. A remote caller of the OpenAI-compatible chat completions endpoint can submit a small, valid video together with request-level media_io_kwargs that select the GLMGA video backend and very large fps and max_frames values. Because the GLMGA sampler constructs and deduplicates an attacker-sized pre-decode frame-index list without a strict work ceiling, a compact request and tiny valid video can consume disproportionate CPU time and memory in the shared media-loading executor, delaying unrelated media requests and causing service degradation or unresponsiveness. The demonstrated impact is a partial denial of service only; no memory corruption, information disclosure, or code execution is involved. The vulnerable path is reachable without vLLM credentials when no API key is configured; with API-key authentication enabled, any caller holding a valid key can trigger it. Red Hat rates this flaw MODERATE (CVSS 3.1 score 5.3, AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L), consistent with the upstream severity. Fixes for the affected Red Hat products are deferred because the impact is moderate with a CVSS score below 7.0, for which Red Hat does not file update trackers; the residual risk is limited to availability degradation of the vLLM service by callers able to reach the chat completions endpoint. 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.