{"id":"CVE-2026-71486","state":"PUBLISHED","title":"vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds","description":"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.","publishedAt":"2026-08-17T20:13:06.289Z","updatedAt":"2026-08-18T12:34:44.986Z","severity":{"score":4.3,"label":"Medium","version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L","source":"GitHub_M"},"assigner":"GitHub_M","products":["vllm-project vllm"],"affected":[{"vendor":"vllm-project","product":"vllm","versions":[{"version":"< 0.26.0","status":"affected"}]}],"references":["https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff","https://github.com/vllm-project/vllm/pull/47260","https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b","https://github.com/vllm-project/vllm/releases/tag/v0.26.0"],"weaknesses":["CWE-400","CWE-770"],"ingestedAt":"2026-10-29T20:12:49.727Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/71xxx/CVE-2026-71486.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-71486","state":"PUBLISHED","datePublished":"2026-08-17T20:13:06.289Z","dateUpdated":"2026-08-18T12:34:44.986Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-08-06T19:56:23.725Z"},"containers":{"cna":{"title":"vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds","descriptions":[{"lang":"en","value":"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."}],"affected":[{"vendor":"vllm-project","product":"vllm","versions":[{"version":"< 0.26.0","status":"affected"}]}],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff","name":"https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/vllm-project/vllm/pull/47260","name":"https://github.com/vllm-project/vllm/pull/47260","tags":["x_refsource_MISC"]},{"url":"https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b","name":"https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b","tags":["x_refsource_MISC"]},{"url":"https://github.com/vllm-project/vllm/releases/tag/v0.26.0","name":"https://github.com/vllm-project/vllm/releases/tag/v0.26.0","tags":["x_refsource_MISC"]}],"metrics":[{"cvssV3_1":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"LOW","baseScore":4.3,"baseSeverity":"MEDIUM","confidentialityImpact":"NONE","integrityImpact":"NONE","privilegesRequired":"LOW","scope":"UNCHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L","version":"3.1"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-400","lang":"en","description":"CWE-400: Uncontrolled Resource Consumption","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-770","lang":"en","description":"CWE-770: Allocation of Resources Without Limits or Throttling","type":"CWE"}]}],"providerMetadata":{"shortName":"GitHub_M","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateUpdated":"2026-08-17T20:13:06.289Z"},"source":{"advisory":"GHSA-8737-qx52-hjff","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-08-18T12:34:35.419144Z","id":"CVE-2026-71486","options":[{"Exploitation":"none"},{"Automatable":"no"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-08-18T12:34:44.986Z"}}]}}}