Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
Not in CISA KEV

CVE-2026-114051 — vllm

CVE-2026-114051 is a CWE-248 vulnerability. A fix is available — see the affected versions and patch details below.

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

Also known asGHSA-4xqp-c3mv-qff7
Published
Updated
Affected
109 versions
Patched
See advisory
Exploits
None indexed
Exploitation data as of Oct 22, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

EPSS Exploitation Probability

via FIRST.org ↗
0.4%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs30th percentile — riskier than 30% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

Description

vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/generate requests with a null max_tokens, so the EngineCore input thread later dies on an uncaught VLLMValidationError while /health still returns 200. Unauthenticated remote attackers can send one request with an oversized min_tokens to hang all subsequent generation requests until manual restart.

Detection & mitigation playbook

Vulnerability
  1. Detect

    Identify every host running the affected component and compare the installed build against the fixed version below — for source-built or distro-packaged software the version string, not a lockfile, is the source of truth (`dpkg -l`, `rpm -q`, or the binary's own `--version`).

  2. Fix

    Upgrade the affected component to the fixed release for CVE-2026-114051, or apply your distribution's backported patch — distro builds are often patched at an older version number, so check your vendor's advisory rather than the upstream version alone.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

Frequently Asked Questions

vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/generate requests with a null max_tokens, so the EngineCore input thread later dies on an uncaught VLLMValidationError while /health still returns 200. Unauthenticated remote attackers can send one request with an oversized min_tokens to hang all subsequent generation requests until manual restart.
O3 Security · Impact-Aware SCA

Is CVE-2026-114051 in your dependencies?

Find it across , including transitive dependencies.

CVE-2026-114051: vllm