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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-55574— vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends

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 0.24.0之前版本存在资源管理错误漏洞，该漏洞源于structured_outputs.regex API参数将用户提供的正则表达式字符串直接传递给语法编译器后端且无编译超时，导致嵌套量词模式可通过所有检查并引发指数级状态空间扩展，允许单个包含对抗性正则表达式的请求无限挂起推理工作线程造成拒绝服务。

AI Predicted 7.5 Difficulty: Easy EPSS 0.58% · P46

Possible ATT&CK Techniques 1 AI

T1499 · Endpoint Denial of Service

Affected Version Matrix 1

VendorProduct Version RangeStatus
vllm-project vllm < 0.24.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-55574

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service. This issue is fixed in version 0.24.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
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 0.24.0之前版本存在资源管理错误漏洞，该漏洞源于structured_outputs.regex API参数将用户提供的正则表达式字符串直接传递给语法编译器后端且无编译超时，导致嵌套量词模式可通过所有检查并引发指数级状态空间扩展，允许单个包含对抗性正则表达式的请求无限挂起推理工作线程造成拒绝服务。
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-project vllm < 0.24.0 -

II. Public POCs for CVE-2026-55574

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

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-55574

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-55574 (2)

Vendor Advisories for CVE-2026-55574 (1)

Same Patch Batch · vllm-project · 2026-07-06 · 4 CVEs total

CVE-2026-54234 7.5 HIGH vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection
CVE-2026-55646 6.5 MEDIUM vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size li
CVE-2026-55514 vLLM denial of service via prompt embeds on M-RoPE models

IV. Related Vulnerabilities

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

V. Comments for CVE-2026-55574

No comments yet

Leave a comment