Investigate in your agent.

Turn this advisory into a focused investigation. Ask your agent to check your project’s versions, explain the evidence, and suggest a compatible fix.

Your agent needs remote MCP support and access to https://cve.new/mcp.

Read the setup guide

Skip to content
cve.new Create a CVE report
Check your stack
CVE-2026-114051high7.5

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

Impact

vLLM before 0.31.0 is vulnerable to a denial of service via min_tokens in /inference/v1/generate, allowing unauthenticated remote attackers to hang generation requests. The issue occurs when a null max_tokens is provided, skipping the min_tokens check. This causes the EngineCore input thread to die on an uncaught VLLMValidationError.

Summarized by @cf/meta/llama-3.3-70b-instruct-fp8-fast. Verify details against the original sources.

Affected packages

This source has no supported package-version data for matching. You can read the advisory here, but this record alone cannot power a dependency check.

Affected products

Vendor version evidence. Product records are separate from automatic dependency matching.

vllm-project · VulnCheck

vllm

2 ranges
VulnCheck version evidence

Package identity

pkg:pypi/vllmExplore vllm →

Identity supplied by VulnCheck. Version matching requires compatible range evidence.

Compare with this publisher’s ranges. This does not inspect your installation.

affected

0 → before 0.31.0

semver versions

unaffected

0.31.0

semver versions

unknown

Other versions: unaffected

Original source 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.

Inside the record

Evidence available

Package identity
Version evidence
Remediation guidance · not supplied
Weakness classification
Additional publishers

Describes the evidence in this view, not whether the product is safe.

Original records

CVE-2026-114051

View the latest unmodified CVE JSON from the official source. It may be newer than this imported page.

cve.new JSON →

Underlying weaknesses

The source’s classification of what caused the vulnerability.

CWE-248 ↗

Uncaught Exception

VulnCheck

Related →

Environment requirements

These conditions apply together as specified by the publisher. A matching product name alone does not establish exposure.

VulnCheck · platform conditions

Any condition may hold

Vulnerable product

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

Before: 0.31.0

Original applicability statements
[
  {
    "nodes": [
      {
        "operator": "OR",
        "negate": false,
        "cpeMatch": [
          {
            "vulnerable": true,
            "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
            "versionEndExcluding": "0.31.0"
          }
        ]
      }
    ]
  }
]
Contributing organizations · 2
VulnCheck

Assigning organization

2026-10-21
CISA-ADP

Additional data publisher

2026-10-28

What changed

Follow changes
No substantive changes have been recorded here yet. History starts when cve.new observes a change after tracking is enabled; earlier edits are not reconstructed.

Large field values are marked as truncated previews. Original source snapshots remain retained.

References

2 sources
github.com/vllm-project/vllm/security/advisories/GHSA-4xqp-c3mv-qff7
vendor-advisoryVulnCheck
www.vulncheck.com/advisories/vllm-before-0.31.0-denial-of-service-via-min-tokens-in-inference-v1-generate
third-party-advisoryVulnCheck