CVE-2026-73556
MediumCVSS 5.3Exploitation Probability (EPSS)
Low risk24th percentile - higher than 24% of all known CVEs
Summary
In vLLM 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.
Risk Assessment
The risk is the possibility of a DoS attack by an unauthenticated user, which could lead to service unavailability and CPU resource exhaustion.
Recommendation
It is recommended to upgrade vLLM to version 0.26.0 or later, which includes a fix for this vulnerability.
Original NVD description (English source)
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.