{"api_version":"1","generated_at":"2026-08-22T05:34:11+00:00","cve":"CVE-2026-71486","urls":{"html":"https://cve.report/CVE-2026-71486","api":"https://cve.report/api/cve/CVE-2026-71486.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-71486","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-71486"},"summary":{"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.","state":"PUBLISHED","assigner":"GitHub_M","published_at":"2026-08-17 20:16:45","updated_at":"2026-08-18 13:17:29"},"problem_types":["CWE-400","CWE-770","CWE-400 CWE-400: Uncontrolled Resource Consumption","CWE-770 CWE-770: Allocation of Resources Without Limits or Throttling"],"metrics":[{"version":"3.1","source":"security-advisories@github.com","type":"Secondary","score":"4.3","severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L","data":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L","baseScore":4.3,"baseSeverity":"MEDIUM","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"LOW","userInteraction":"NONE","scope":"UNCHANGED","confidentialityImpact":"NONE","integrityImpact":"NONE","availabilityImpact":"LOW"}},{"version":"3.1","source":"CNA","type":"DECLARED","score":"4.3","severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L","data":{"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"}}],"references":[{"url":"https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b","name":"https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/vllm-project/vllm/pull/47260","name":"https://github.com/vllm-project/vllm/pull/47260","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"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","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/vllm-project/vllm/releases/tag/v0.26.0","name":"https://github.com/vllm-project/vllm/releases/tag/v0.26.0","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-71486","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-71486","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"vllm-project","product":"vllm","version":"affected < 0.26.0","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":{"cve_year":"2026","cve_id":"71486","cve":"CVE-2026-71486","epss":"0.003410000","percentile":"0.271560000","score_date":"2026-08-18","updated_at":"2026-08-19 00:07:28"},"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"adp":[{"metrics":[{"other":{"content":{"id":"CVE-2026-71486","options":[{"Exploitation":"none"},{"Automatable":"no"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","timestamp":"2026-08-18T12:34:35.419144Z","version":"2.0.3"},"type":"ssvc"}}],"providerMetadata":{"dateUpdated":"2026-08-18T12:34:44.986Z","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","shortName":"CISA-ADP"},"title":"CISA ADP Vulnrichment"}],"cna":{"affected":[{"product":"vllm","vendor":"vllm-project","versions":[{"status":"affected","version":"< 0.26.0"}]}],"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."}],"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","description":"CWE-400: Uncontrolled Resource Consumption","lang":"en","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-770","description":"CWE-770: Allocation of Resources Without Limits or Throttling","lang":"en","type":"CWE"}]}],"providerMetadata":{"dateUpdated":"2026-08-17T20:13:06.289Z","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M"},"references":[{"name":"https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff","tags":["x_refsource_CONFIRM"],"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff"},{"name":"https://github.com/vllm-project/vllm/pull/47260","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/pull/47260"},{"name":"https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b"},{"name":"https://github.com/vllm-project/vllm/releases/tag/v0.26.0","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/releases/tag/v0.26.0"}],"source":{"advisory":"GHSA-8737-qx52-hjff","discovery":"UNKNOWN"},"title":"vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds"}},"cveMetadata":{"assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","assignerShortName":"GitHub_M","cveId":"CVE-2026-71486","datePublished":"2026-08-17T20:13:06.289Z","dateReserved":"2026-08-06T19:56:23.725Z","dateUpdated":"2026-08-18T12:34:44.986Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-08-17 20:16:45","lastModifiedDate":"2026-08-18 13:17:29","problem_types":["CWE-400","CWE-770","CWE-400 CWE-400: Uncontrolled Resource Consumption","CWE-770 CWE-770: Allocation of Resources Without Limits or Throttling"],"metrics":{"cvssMetricV31":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L","baseScore":4.3,"baseSeverity":"MEDIUM","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"LOW","userInteraction":"NONE","scope":"UNCHANGED","confidentialityImpact":"NONE","integrityImpact":"NONE","availabilityImpact":"LOW"},"exploitabilityScore":2.8,"impactScore":1.4}],"ssvcV203":[{"source":"134c704f-9b21-4f2e-91b3-4a467353bcc0","ssvcData":{"timestamp":"2026-08-18T12:34:35.419144Z","id":"CVE-2026-71486","options":[{"exploitation":"none"},{"automatable":"no"},{"technicalImpact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"71486","Ordinal":"1","Title":"vLLM: Derender endpoints decode caller-supplied GenerateResponse","CVE":"CVE-2026-71486","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"71486","Ordinal":"1","NoteData":"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.","Type":"Description","Title":"vLLM: Derender endpoints decode caller-supplied GenerateResponse"}]}}}