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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2025-62426— vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

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 0.5.5版本至0.11.1之前版本存在安全漏洞，该漏洞源于chat_template_kwargs参数验证不足，可能导致API服务器处理阻塞。

CVSS 6.5 · Medium EPSS 0.37% · P29

Possible ATT&CK Techniques 1 AI

T1499 · Endpoint Denial of Service
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2025-62426

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.
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 0.5.5版本至0.11.1之前版本存在安全漏洞，该漏洞源于chat_template_kwargs参数验证不足，可能导致API服务器处理阻塞。
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 >= 0.5.5, < 0.11.1 -

II. Public POCs for CVE-2025-62426

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

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2025-62426

请登录查看更多情报信息。

Vendor Advisories for CVE-2025-62426 (1)

Same Patch Batch · vllm-project · 2025-11-21 · 3 CVEs total

CVE-2025-62164 8.8 HIGH VLLM deserialization vulnerability leading to DoS and potential RCE
CVE-2025-62372 vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

IV. Related Vulnerabilities

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

V. Comments for CVE-2025-62426

No comments yet

Leave a comment