High [CVE-2026-55574] Denial of Service via adversarial regular expression in structured outputs API

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. A remote attacker could exploit this vulnerability by providing a specially crafted regular expression to the structured_outputs.regex API parameter.

This results in a Denial of Service (DoS) for the affected system. An Important denial of service vulnerability exists in vLLM, as utilized within Red Hat AI Inference Server and Red Hat OpenShift AI.

Red Hat severity: Important — CVSS 7.5 (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H). Weakness: CWE-1333.

Affected products named by the advisory: Red Hat AI Inference Server 3.2; Red Hat AI Inference Server 3.3; Red Hat AI Inference Server 3.4; Red Hat Enterprise Linux AI 3.4; and 2 more.