{"id":"CVE-2026-116181","title":"vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids","summary":"vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or b…","severity":"medium","cvss":6.5,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","cvssSource":"cna","cwe":["CWE-129"],"vendor":"vllm-project","product":"vllm","affected":["vllm >= 0.20.1 < 0.29.0"],"published":"2026-10-25","updated":"2026-10-25","sourceUpdated":"2026-10-25T13:20:19.874Z","source":"CVEORG","sourceUrl":"https://www.cve.org/CVERecord?id=CVE-2026-116181","references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-w9r6-29q4-pvpr","label":"GitHub Security Advisory (GHSA-w9r6-29q4-pvpr)"},{"url":"https://www.vulncheck.com/advisories/vllm-0.20.1-before-0.29.0-dos-and-gpu-out-of-bounds-write-via-stop-token-ids","label":"VulnCheck Advisory: vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids"}],"tags":["cve.org"],"ingestedAt":"2026-10-25T22:08:29.945Z","slug":"CVE-2026-116181","body":"## Overview\n\nvLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.\n\n## Affected\n\n- `vllm >= 0.20.1 < 0.29.0`\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.","depth":"sunlit","depthScore":36,"depthScoreParts":{"impact":35.8,"likelihood":0,"exploitation":0,"ransomware":0},"changes":[]}