{"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…","summary":"vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker 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,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["vLLM"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":"vLLM memory exhaustion via max_tokens=0 requests in prefill/decode deployments","headlinePromptVersion":"h1","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":0.00755,"epssCheckedAt":"2026-11-04T18:09:14.050Z","kevDateAdded":null,"advisoryAliases":["GHSA-jh5x-pggf-m4cr"],"affectedPackagesSource":null,"affectedPackagesCheckedAt":"2026-11-01T00:10:40.525Z","patchAvailable":null,"disclosureDate":"2026-09-17T23:18:54.710Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"trivial","impactType":["availability"],"aiComponentTargeted":"inference","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":null,"atlasIds":null,"fixes":[]}}