{"data":{"id":"11af4fa1-1be8-4959-9b02-2ba3b47e815f","title":"CVE-2026-93436: vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode di","summary":"vLLM (a software framework for running large language models) versions up to 0.29.0 has a memory cleanup bug in its decode workers (specialized processors that handle the generation phase of AI inference). Attackers can exploit this by sending requests with max_tokens=0 (asking for zero output tokens), which prevents the system from properly clearing temporary data, eventually consuming all available memory until the worker crashes and restarts.","solution":"N/A -- no mitigation discussed in source.","labels":["security"],"sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-93436","publishedAt":"2026-09-17T23:18:54.710Z","cveId":"CVE-2026-93436","cweIds":["CWE-401"],"cvssScore":"7.5","cvssSeverity":"high","severity":"high","attackType":["denial_of_service"],"issueType":"vulnerability","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":["vLLM"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","attackVector":"network","attackComplexity":"low","privilegesRequired":"none","userInteraction":"none","exploitMaturity":"unknown","epssScore":0,"patchAvailable":null,"disclosureDate":"2026-09-17T23:18:54.710Z","capecIds":null,"crossRefCount":0,"attackSophistication":"trivial","impactType":["availability"],"aiComponentTargeted":"inference","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":null,"atlasIds":null}}