{
  "id": "CVE-2026-100651",
  "url": "https://poc.griffinguard.io/cve/CVE-2026-100651",
  "published_at": "2026-09-26T13:23:21.141Z",
  "title": "vllm before 0.29.0 Denial of Service via Decoder Prompt Length Bypass",
  "vendor": "vllm-project",
  "product": "vllm",
  "cvss": {
    "score": 7.1,
    "source": "cna",
    "vector": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N"
  },
  "kev": {
    "in_kev": false,
    "added_at": null,
    "days_after_publication": null
  },
  "first_poc": null,
  "poc_repo_count": 0,
  "exploit_count": 0,
  "suspicious_repo_count": 0,
  "edge_device": null,
  "description": "vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' (multimodal) payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied token_ids, and GenerateRequest.token_ids (vllm/entrypoints/serve/disagg/protocol.py) is not checked against model_config.max_model_len. For multimodal processors that report skip_prompt_length_check=True (for example Nemotron Parse, Whisper, and FireRedLID), InputProcessor._validate_prompt_len() returns immediately for both encoder and decoder prompts, so an overlong prompt becomes an EngineCoreRequest and reaches the worker input-batch copy into a fixed max_model_len-wide NumPy row. A client able to reach the endpoint on an affected model configuration can therefore submit an overlong token_ids list to trigger a worker failure and denial of service. Fixed in 0.29.0.",
  "cwe": "CWE-400",
  "cpes": [
    "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*"
  ],
  "cvss_by_source": {
    "cna": 7.1
  },
  "repos": [],
  "remediation": {
    "affected": [
      {
        "vendor": "vllm-project",
        "product": "vllm",
        "ranges": [
          "\u003c 0.29.0"
        ],
        "fixed_in": [
          "0.29.0"
        ]
      }
    ],
    "upgrade": [
      "Upgrade vllm to 0.29.0 or later."
    ],
    "references": [
      {
        "kind": "Vendor advisory",
        "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-3mqx-f33v-vgp9"
      }
    ]
  },
  "exploit_refs": [],
  "hunt_profile": [],
  "rules": []
}
