PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-114051 vllm-project CVE debrief

CVE-2026-114051 is a high-severity vulnerability in vLLM before 0.31.0, allowing unauthenticated remote attackers to cause a denial of service via the /inference/v1/generate endpoint. The vulnerability is caused by the lack of a check for min_tokens <= max_tokens when max_tokens is null, leading to a VLLMValidationError that can hang all subsequent generation requests.

Vendor
vllm-project
Product
vllm
CVSS
HIGH 7.1
CISA KEV
Not listed in stored evidence
Original CVE published
2026-10-21
Original CVE updated
2026-10-28
Advisory published
2026-10-21
Advisory updated
2026-10-28

Who should care

Defenders responsible for vLLM deployments should assess exposure and prioritize verification and remediation. This includes reviewing the version of vLLM in use, monitoring the /inference/v1/generate endpoint for suspicious activity, and implementing additional security measures to prevent exploitation. Security teams and vulnerability management teams should also be aware of the potential impact and take necessary actions to mitigate the vulnerability.

Why it matters

CVE-2026-114051 is a high-severity vulnerability in vLLM before 0.31.0, allowing unauthenticated remote attackers to cause a denial of service. Defenders should prioritize verifying the version of vLLM in use and upgrading to 0.31.0 or later to prevent exploitation.

  • Denial of service via /inference/v1/generate endpoint
  • Potential disruption of generation requests
  • Need for verification of vLLM version and potential upgrade

Technical summary

The vulnerability is caused by the lack of a check for min_tokens <= max_tokens when max_tokens is null, leading to a VLLMValidationError that can hang all subsequent generation requests. This occurs in the /inference/v1/generate endpoint of vLLM before 0.31.0. The error can cause denial of service via the endpoint. Unauthenticated remote attackers can send one request with an oversized min_tokens to hang all subsequent generation requests until manual restart. The vulnerability has a CVSS score of 7.1 and a HIGH severity rating.

Defensive priority

Defenders should prioritize verifying the version of vLLM in use and upgrading to 0.31.0 or later to prevent exploitation.

Recommended defensive actions

  • Verify the version of vLLM in use and upgrade to 0.31.0 or later
  • Monitor the /inference/v1/generate endpoint for suspicious activity
  • Implement additional security measures to prevent exploitation
  • 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 source item provide details on the vulnerability, including its cause and potential impact. However, there is limited information on potential exploits or attacks. To verify, defenders should review the official CVE record, source item, and vendor advisories. The vulnerability is caused by a lack of check for min_tokens <= max_tokens when max_tokens is null, leading to a VLLMValidationError. Limited public information exists on potential exploits.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-114051 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-114051

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

  • CVE-2026-114051 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-114051

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

Supplemental references

  • vLLM before 0.31.0 Denial of Service via min_tokens in /inference/v1/generate

    Unverified legacy reference

    URL: https://raw.githubusercontent.com/CVEProject/cvelistV5/main/cves/2026/114xxx/CVE-2026-114051.json

    cve_program_cvelist_v5

  • Source reference

    Unverified legacy reference

    URL: https://github.com/vllm-project/vllm/security/advisories/GHSA-4xqp-c3mv-qff7

    Supplemental source - vendor-advisory

  • Source reference

    Unverified legacy reference

    URL: https://www.vulncheck.com/advisories/vllm-before-0.31.0-denial-of-service-via-min-tokens-in-inference-v1-generate

    Supplemental source - third-party-advisory

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.