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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2025-71379— vllm - Regular Expression Denial of Service in Multiple Components

Quick assessment

Affected
vllm 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 0.6.3版本至0.9.0之前版本存在源管理错误漏洞，该漏洞源于vllm/lora/utils.py、phi4mini工具解析器和OpenAI兼容服务聊天端点中的多个正则表达式模式存在灾难性回溯，可能导致攻击者通过提交带有嵌套或重复结构的特制输入触发严重的CPU消耗和性能下降，导致拒绝服务。

CVSS 4.3 · Medium EPSS 0.48% · P40

Possible ATT&CK Techniques 1 AI

T1499 · Endpoint Denial of Service

Affected Version Matrix 2

VendorProduct Version RangeStatus
vllm vllm 0.6.3< 0.9.0 affected
0.9.0 unaffected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2025-71379

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 - Regular Expression Denial of Service in Multiple Components
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker submitting crafted input with nested or repeated structures can trigger severe CPU consumption and performance degradation, resulting in denial of service.
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:L
Source: CVE Program / CVE List V5
Vulnerability Type
CWE-1333
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 资源管理错误漏洞
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 0.6.3版本至0.9.0之前版本存在源管理错误漏洞，该漏洞源于vllm/lora/utils.py、phi4mini工具解析器和OpenAI兼容服务聊天端点中的多个正则表达式模式存在灾难性回溯，可能导致攻击者通过提交带有嵌套或重复结构的特制输入触发严重的CPU消耗和性能下降，导致拒绝服务。
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 0.6.3 ~ 0.9.0 -

II. Public POCs for CVE-2025-71379

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

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2025-71379

请登录查看更多情报信息。

Vendor Advisories for CVE-2025-71379 (2)

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm
Same weakness: CWE-1333

V. Comments for CVE-2025-71379

No comments yet

Leave a comment