{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-71486", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-08-06T19:56:23.725Z", "datePublished": "2026-08-17T20:13:06.289Z", "dateUpdated": "2026-08-18T12:34:44.986Z"}, "containers": {"cna": {"title": "vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds", "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"}]}], "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"}}], "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"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": "< 0.26.0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-08-17T20:13:06.289Z"}, "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."}], "source": {"advisory": "GHSA-8737-qx52-hjff", "discovery": "UNKNOWN"}}, "adp": [{"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"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-08-18T12:34:44.986Z"}}]}}

{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-71486", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-08-06T19:56:23.725Z", "datePublished": "2026-08-17T20:13:06.289Z", "dateUpdated": "2026-08-18T12:34:44.986Z"}, "containers": {"cna": {"title": "vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds", "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"}]}], "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"}}], "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"}], "affected": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"version": "< 0.26.0", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-08-17T20:13:06.289Z"}, "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."}], "source": {"advisory": "GHSA-8737-qx52-hjff", "discovery": "UNKNOWN"}}, "adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-71486", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "partial"}], "version": "2.0.3", "timestamp": "2026-08-18T12:34:35.419144Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-08-18T12:34:40.788Z"}}]}}

{"affected": [{"affectedData": [{"product": "vllm", "vendor": "vllm-project", "versions": [{"status": "affected", "version": "< 0.26.0"}]}], "source": "security-advisories@github.com"}], "cveTags": [], "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."}], "id": "CVE-2026-71486", "lastModified": "2026-08-18T13:17:29.203", "metrics": {"cvssMetricV31": [{"cvssData": {"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"}, "exploitabilityScore": 2.8, "impactScore": 1.4, "source": "security-advisories@github.com", "type": "Secondary"}], "ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-71486", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "role": "CISA Coordinator", "timestamp": "2026-08-18T12:34:35.419144Z", "version": "2.0.3"}}]}, "published": "2026-08-17T20:16:45.927", "references": [{"source": "security-advisories@github.com", "url": "https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b"}, {"source": "security-advisories@github.com", "url": "https://github.com/vllm-project/vllm/pull/47260"}, {"source": "security-advisories@github.com", "url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0"}, {"source": "security-advisories@github.com", "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Received", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-400"}, {"lang": "en", "value": "CWE-770"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "semver", "value": "[0,0.26.0)"}}], "enrichment": {"confidence": 100.0, "confidence_source": "matching", "scores": [{"score": 100.0, "source": "matching"}]}, "original": {"product": "vllm", "source": "cna", "vendor": "vllm-project"}, "product": "vllm", "vendor": "vllm-project"}], "created": "2026-08-17T21:45:02.940152+00:00", "updated": "2026-08-17T21:45:03.116172+00:00", "vendors": ["vllm-project", "vllm-project$PRODUCT$vllm"]}