VULNERABILITY INTELLIGENCE

CVE-2026-73556

CVSS score5.3 MEDIUM
EPSS probability0.52%
CISA KEVNot currently listed
Published2026-08-13
Last modified2026-09-28
CVSS vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L

Description

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format_enforcer, allowing an unauthenticated /v1/completions request against the lm-format-enforcer backend to consume a CPU core and stall the structured-output engine path with a catastrophic regular expression. This issue is fixed in version 0.26.0.

Weakness classification

  • security-advisories@github.com: CWE-400

Primary references