{
  "affected": [
    {
      "ranges": [
        {
          "database_specific": {
            "extracted_events": [
              {
                "introduced": "0"
              },
              {
                "fixed": "0.29.0"
              }
            ],
            "source": [
              "DESCRIPTION",
              "REFERENCES"
            ]
          },
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "98dff2a81d747d1dba01a47f939f48c3526d4206"
            },
            {
              "fixed": "752a3a504485790a2e8491cacbb35c137339ad34"
            }
          ],
          "repo": "https://github.com/vllm-project/vllm",
          "type": "GIT"
        }
      ]
    }
  ],
  "aliases": [
    "GHSA-p6g9-7v3x-m8mv"
  ],
  "database_specific": {
    "cna_assigner": "VulnCheck",
    "cwe_ids": [
      "CWE-400"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/100xxx/CVE-2026-100650.json"
  },
  "details": "vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact.",
  "id": "CVE-2026-100650",
  "modified": "2026-09-28T03:30:48.149244222Z",
  "published": "2026-09-26T13:23:20.418Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/100xxx/CVE-2026-100650.json"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-100650"
    },
    {
      "type": "ADVISORY",
      "url": "https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-exhaustion-via-unbounded-media-materialization"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/commit/752a3a504485790a2e8491cacbb35c137339ad34"
    }
  ],
  "schema_version": "1.9.0",
  "severity": [
    {
      "score": "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",
      "type": "CVSS_V4"
    }
  ],
  "summary": "vLLM before 0.29.0 Resource Exhaustion via Unbounded Media Materialization"
}