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.
CVSS Details
- CVSS 3.1 Base Score: 5.3
- CVSS 3.1 Vector: (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L)
Prioritise with Active Threat Intelligence
With curated Threat Intelligence, you can see which vulnerabilities truly put you at risk, prioritize what matters most, and act before attackers do.
Explore Intelligence Hub