{
  "affected": [
    {
      "ranges": [
        {
          "database_specific": {
            "extracted_events": [
              {
                "introduced": "0"
              },
              {
                "fixed": "0.26.0"
              }
            ],
            "source": [
              "AFFECTED_FIELD",
              "REFERENCES"
            ]
          },
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "8e61b646e2d157f9b93451fa048f9c8530c8a67b"
            },
            {
              "fixed": "ffd46bfab2128bb84146050e98b51a617c6575ab"
            }
          ],
          "repo": "https://github.com/vllm-project/vllm",
          "type": "GIT"
        }
      ]
    }
  ],
  "aliases": [
    "GHSA-8737-qx52-hjff"
  ],
  "database_specific": {
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
      "CWE-400",
      "CWE-770"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/71xxx/CVE-2026-71486.json"
  },
  "details": "vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures are processed by OnlineDerenderer and tokenizer.decode before max_model_len, max_tokens, max_num_seqs, or response-size limits are enforced, allowing an authenticated API client to consume excessive CPU and memory and produce oversized responses. This issue is fixed in version 0.26.0.",
  "id": "CVE-2026-71486",
  "modified": "2026-09-11T03:30:20.024740389Z",
  "published": "2026-08-17T20:13:06.289Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/71xxx/CVE-2026-71486.json"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-71486"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b"
    },
    {
      "type": "FIX",
      "url": "https://github.com/vllm-project/vllm/pull/47260"
    }
  ],
  "schema_version": "1.9.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds"
}