{"data":{"id":"abd7da11-9144-4966-944e-dfef66fbc048","title":"CVE-2026-93592: vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, ","summary":"vLLM (a tool for running large language models) versions before 0.28.0 have a vulnerability where two endpoints (/v1/embeddings and /pooling) don't properly check if token IDs (numeric identifiers representing words) are valid. An attacker can send a request with a negative token ID to crash the system, and because this triggers a CUDA assertion (an error check on the GPU, the specialized processor used for AI), it corrupts the GPU's state and breaks all future requests until the service restarts.","solution":"Update vLLM to version 0.28.0 or later.","labels":["security"],"sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-93592","publishedAt":"2026-09-18T14:19:10.267Z","cveId":"CVE-2026-93592","cweIds":["CWE-129"],"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":"2026-09-18T14:19:10.267Z","capecIds":null,"crossRefCount":0,"attackSophistication":"trivial","impactType":["availability"],"aiComponentTargeted":"inference","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":null,"atlasIds":null}}