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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-56340— vLLM - Denial of Service via Unvalidated Multimodal Embeddings

Quick assessment

Affected
vLLM vLLM
Exploitation
Public or AI PoC available; prioritize validation
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.10.2版本至0.11.1之前版本存在输入验证错误漏洞，该漏洞源于多模态嵌入处理中缺少稀疏张量验证，可能导致攻击者在prompt-embeds功能启用时发送特制嵌入请求，触发崩溃或资源耗尽，并存在越界内存破坏风险。

CVSS 8.8 · High EPSS 0.64% · P49

Affected Version Matrix 2

VendorProduct Version RangeStatus
vLLM vLLM 0.10.2< 0.13.0 affected
0.13.0 unaffected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-56340

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 - Denial of Service via Unvalidated Multimodal Embeddings
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
输入验证不恰当
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 输入验证错误漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.10.2版本至0.11.1之前版本存在输入验证错误漏洞，该漏洞源于多模态嵌入处理中缺少稀疏张量验证，可能导致攻击者在prompt-embeds功能启用时发送特制嵌入请求，触发崩溃或资源耗尽，并存在越界内存破坏风险。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
vLLM vLLM 0.10.2 ~ 0.13.0 -

II. Public POCs for CVE-2026-56340

# POC Description Source Link Shenlong Link
AI-Generated POC Premium
Qwen3.6-35B-A3B · 7420 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month

III. Intelligence Information for CVE-2026-56340

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-56340 (2)

IV. Related Vulnerabilities

Same product: vLLM
Same vendor: vLLM
Same weakness: CWE-20

V. Comments for CVE-2026-56340

No comments yet

Leave a comment