CVE-2026-71486

{"id": "CVE-2026-71486", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-71486", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-08-18T12:34:35.419144Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 4.3, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "LOW", "privilegesRequired": "LOW", "confidentialityImpact": "NONE"}, "impactScore": 1.4, "exploitabilityScore": 2.8}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "vllm-project", "product": "vllm", "versions": [{"status": "affected", "version": "< 0.26.0"}]}]}], "published": "2026-08-17T20:16:45.927", "references": [{"url": "https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b", "tags": ["Patch"], "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/pull/47260", "tags": ["Issue Tracking", "Patch"], "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0", "tags": ["Release Notes"], "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff", "tags": ["Exploit", "Vendor Advisory", "Mitigation"], "source": "security-advisories@github.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-400"}, {"lang": "en", "value": "CWE-770"}]}], "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."}, {"lang": "es", "value": "vLLM es un motor de inferencia y servicio para grandes modelos de lenguaje. Antes de la versi\u00f3n 0.26.0, los puntos finales /v1/completions/derender y /v1/chat/completions/derender aceptan objetos GenerateResponse proporcionados por el llamador cuyas estructuras generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs y routed_experts son procesadas por OnlineDerenderer y tokenizer.decode antes de que se apliquen los l\u00edmites de max_model_len, max_tokens, max_num_seqs o tama\u00f1o de respuesta, permitiendo a un cliente API autenticado consumir CPU y memoria excesivas y producir respuestas sobredimensionadas. Este problema se corrige en la versi\u00f3n 0.26.0."}], "lastModified": "2026-10-23T16:10:00.313", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "BB265B9E-EBAE-4833-8C3E-B203C8E9EC86", "versionEndExcluding": "0.26.0"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}