All vulnerabilities

Servers and applications

CVE-2026-105760

GLMGA video sampling permits request-driven CPU and memory exhaustion

Severity
Medium 5.3
Published
23 Sept 2026
Last changed
16 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.30.0
Exploit chance
0.3% in the next 30 daysHigher than 22% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Uncontrolled resource consumption (CWE-400)
Attack
Over the network · No login needed · No user action needed
Attacker can
Slow it down
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
Also known as
GHSA-58v5-2m8f-94pr
Sources
NVD, CVE Program, Project advisories (GitHub)

Description

The OpenAI-compatible chat endpoint accepts request-level video loader options through media_io_kwargs. A caller can select the GLMGA sampler and provide large fps and max_frames values. GLMGA first constructs an attacker-sized Python index list and then deduplicates it, even when the supplied video contains only a few frames. This work occurs in the shared media-loading executor before frame reads, allowing a tiny valid video and compact JSON options to consume disproportionate CPU time and memory and delay unrelated media requests.

The demonstrated impact is partial denial of service. No memory corruption, data disclosure, or code execution is claimed.

A remote caller submits a valid chat-completion request with a small video and the following request-level options:

Increasing both numeric values increases temporary list construction and deduplication work even when the final decoded frame set remains unchanged.

From vllm-project/vllm's security advisory. Shortened; the full text is there.

Workarounds

  • Remove or filter request-level video_backend, fps, and max_frames options at the gateway.
  • Do not allow untrusted callers to select GLMGA.
  • Apply authentication, rate limiting, request concurrency limits, and process memory isolation.
  • Use a separate constrained media-loading worker pool where operationally feasible.
  • Existing media byte, pixel, or decoded-frame limits do not necessarily bound this pre-decode candidate-index allocation.
Workarounds as given by vllm-project/vllm's security advisory.

Affected software

SoftwareAffected versions
vLLMServers and applications · cna:vllm-project|vllm
  • From 0.23.0rc2 before 0.30.0
vLLMServers and applications · cpe:a:vllm:vllm
  • From 0.23.0 before 0.30.0
vLLMServers and applications · github:vllm-project/vllm
  • From 0.23.0rc2 before 0.30.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-105760
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-105760
  • GitHub Advisory Database https://github.com/advisories/GHSA-58v5-2m8f-94pr
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94pr