PT-2026-56000 · Vllm · Vllm

Brodmart · Published 2026-07-06 · Updated 2026-07-06 · CVE-2026-55574

NVD

CVSS v4.0

8.7

High

Base vector

AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

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.

Fix

DoS

Weakness Enumeration

CWE-1333

Related Identifiers

CVE-2026-55574

Affected Products

Vllm

References · 4

• https://nvd.nist.gov/vuln/detail/CVE-2026-55574 · Security Note
• https://github.com/vllm-project/vllm/commit/2b3006076c5e9bc4cda9e03e3641388de3c5c286 · Note
• https://github.com/vllm-project/vllm/security/advisories/GHSA-rwxx-mrjm-wc2m · Note
• https://github.com/vllm-project/vllm/pull/45118 · Note