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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-34756— vLLM Affected by Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server

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vLLM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 0.1.0至0.19.0之前版本存在安全漏洞，该漏洞源于ChatCompletionRequest和CompletionRequest Pydantic模型中n参数缺少上限验证，可能导致未经验证的攻击者通过发送单个HTTP请求造成拒绝服务攻击。

CVSS 6.5 · Medium EPSS 0.77% · P54

Affected Version Matrix 1

VendorProduct Version RangeStatus
vllm-project vllm >= 0.1.0, < 0.19.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-34756

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 Affected by Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
不加限制或调节的资源分配
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
vLLM是vLLM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 0.1.0至0.19.0之前版本存在安全漏洞，该漏洞源于ChatCompletionRequest和CompletionRequest Pydantic模型中n参数缺少上限验证，可能导致未经验证的攻击者通过发送单个HTTP请求造成拒绝服务攻击。
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-project vllm >= 0.1.0, < 0.19.0 -

II. Public POCs for CVE-2026-34756

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

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-34756

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-34756 (1)

Vendor Advisories for CVE-2026-34756 (1)

Same Patch Batch · vllm-project · 2026-04-06 · 3 CVEs total

CVE-2026-34755 6.5 MEDIUM vLLM Affected by Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processi
CVE-2026-34753 5.4 MEDIUM vLLM affected by Server-Side Request Forgery (SSRF) in `download_bytes_from_url `

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-770

V. Comments for CVE-2026-34756

No comments yet

Leave a comment