PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-73556 vllm-project CVE debrief

A vulnerability in vLLM, an inference and serving engine for large language models, allows an unauthenticated /v1/completions request 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. The vulnerability is caused by the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py being passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation.

Vendor
vllm-project
Product
vllm
CVSS
MEDIUM 5.3
CISA KEV
Not listed in stored evidence
Original CVE published
2026-08-13
Original CVE updated
2026-09-09
Advisory published
2026-08-13
Advisory updated
2026-09-09

Who should care

Defenders responsible for vLLM deployments should assess exposure to this vulnerability and prioritize upgrading to version 0.26.0 or later. They should also verify the affected scope, severity, and vendor guidance, and plan vendor-supported updates or mitigations through normal change control where exposure is confirmed.

Why it matters

Defenders should prioritize verifying exposure to this vulnerability and upgrading to version 0.26.0 or later to prevent potential CPU core consumption and engine stall via catastrophic regular expression.

  • Potential CPU core consumption and engine stall via catastrophic regular expression
  • Verification of exposure and remediation priority

Technical summary

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, allowing an unauthenticated /v1/completions request to consume a CPU core and stall the structured-output engine path. This issue is fixed in version 0.26.0. The vulnerability allows an unauthenticated request to cause a denial-of-service (DoS) attack on the affected system, which could lead to a consumption of a CPU core and stall the structured-output engine path.

Defensive priority

Defenders should prioritize verifying exposure to this vulnerability and upgrading to version 0.26.0 or later.

Recommended defensive actions

  • Verify exposure to this vulnerability in vLLM deployments
  • Upgrade to version 0.26.0 or later
  • Monitor for unauthenticated /v1/completions requests
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up

Evidence notes

The CVE record and NVD entry provide details on the vulnerability, but the scope of affected versions and deployments requires further verification. 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, allowing an unauthenticated /v1/completions request to consume a CPU core and stall the structured-output engine path. Defenders should verify exposure to this vulnerability and prioritize upgrading to

Sources and references

Verified primary and authoritative sources

  • CVE-2026-73556 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-73556

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-73556 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-73556

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.