{"id":"CVE-2026-116178","published":"2026-10-25T14:16:57.483","lastModified":"2026-10-26T20:17:53.627","description":"vLLM from 0.20.0 before 0.30.0 contains a denial of service vulnerability that allows remote attackers to crash the engine by sending inconsistent multimodal metadata to the disaggregated /inference/v1/generate endpoint. Attackers can replay a valid multimodal item with repeated or overlapping mm_placeholders ranges or mismatched kwargs_data and mm_hashes lists, producing a negative text span in Qwen2.5-VL position construction that terminates the engine.","cvssScore":5.9,"cvssSeverity":"MEDIUM","cvssVector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H","cwes":["CWE-20"],"vendors":[],"products":[],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-34qw-q2h2-jp3m","tags":[]},{"url":"https://www.vulncheck.com/advisories/vllm-0.20.0-before-0.30.0-dos-via-inference-v1-generate-mm-placeholders","tags":[]}],"exploitRefs":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-34qw-q2h2-jp3m","tags":[]}],"hasPoc":true,"ai":null}