Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-105760— vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion

Quick assessment

Affected
vllm-project vllm
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

vLLM 是专为大语言模型构建的推理与 Serving 引擎。在版本 0.30.0 之前，攻击者可通过请求级别的 media_io_kwargs 字段选择 GLMGA 视频后端，并为 fps 和 max_frames 选项传入极大的值，且系统未设置严格的工作量上限。GLMGA 会构造并去重一个由攻击者控制大小的预解码帧索引列表，从而导致一个紧凑的请求和极小的有效视频即可在共享的媒体加载执行器中消耗不成比例的 CPU 时间和内存资源。该问题已在 0.30.0 版本中修复。

CVSS 5.3 · Medium
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-105760

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
Source: CVE Program / CVE List V5
Vulnerability Type
未加控制的资源消耗(资源穷尽)
Source: CVE Program / CVE List V5

Affected Products

Vendor Product Affected Versions CPE Subscribe
vllm-project vllm >= 0.23.0rc2, < 0.30.0 -

II. Public POCs for CVE-2026-105760

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-105760

请登录查看更多情报信息。

Other References for CVE-2026-105760 (4)

Same Patch Batch · vllm-project · 2026-10-05 · 9 CVEs total

CVE-2026-105753 6.5 MEDIUM vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reu
CVE-2026-105754 6.5 MEDIUM vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features
CVE-2026-105756 6.5 MEDIUM vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP de
CVE-2026-105757 6.5 MEDIUM vLLM: Structured-output request errors escape the request boundary and terminate the share
CVE-2026-105759 5.9 MEDIUM vLLM: Unbounded Prometheus label cardinality from attacker-controlled HTTP method tokens i
CVE-2026-105758 5.3 MEDIUM vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the
CVE-2026-105755 4.2 MEDIUM vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled req
CVE-2026-105752 3.1 LOW vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-400

V. Comments for CVE-2026-105760

No comments yet

Leave a comment