cve.bz

CVE-2026-73556

5.3 mediumEPSS 0.5%

Medium (5.3) in vllm vllm. EPSS 0.5% chance of exploitation in the next 30 days. Fixed in vllm 0.26.0.

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.

Severity

CVSS 3.1

5.3 medium
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
EPSS
0.5% chance of exploitation in the next 30 days; higher than 43% of CVEs (scores of 2026-10-31)
CWEs
CWE-400, CWE-1333
Published
Modified
Record from
the NVD, synced

Affected

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-48jh-3gj7-fg8vPyPIvllm<0.26.00.26.0
PYSEC-2026-3933PyPIvllm<0.26.00.26.0

References

Check your stackJSON