{"id":"CVE-2026-116180","published":"2026-10-25T14:16:57.760","lastModified":"2026-10-26T20:17:53.793","description":"vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, making tokenizer decode raise OverflowError, which crashes EngineCore and drops all co-tenant requests.","cvssScore":7.7,"cvssSeverity":"HIGH","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H","cwes":["CWE-908"],"vendors":[],"products":[],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-rhcx-5729-88vg","tags":[]},{"url":"https://www.vulncheck.com/advisories/vllm-from-0.8.5-before-0.31.0-cross-tenant-dos-via-uninitialized-logprobstensors","tags":[]}],"exploitRefs":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-rhcx-5729-88vg","tags":[]}],"hasPoc":true,"ai":null}