CVE-2026-55574

描述

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.

如何修補 CVE-2026-55574

要修補 CVE-2026-55574,請將受影響套件升級到下列已修補版本。

• —升級至 0.24.0 或更新版本

CVE-2026-55574 正在被利用嗎?

低 — EPSS 為 0.3%,目前沒有觀察到大規模利用活動。

受影響套件(1)

• from 0, < 0.24.0

CVSS 分數

參考連結(6)

• ADVISORYnvd.nist.gov/vuln/detail/CVE-2026-55574
• PATCHgithub.com/vllm-project/vllm
• WEBgithub.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2304.yaml
• WEBgithub.com/vllm-project/vllm/commit/2b3006076c5e9bc4cda9e03e3641388de3c5c286