CVE-2026-116180

high

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.

References

https://www.vulncheck.com/advisories/vllm-from-0.8.5-before-0.31.0-cross-tenant-dos-via-uninitialized-logprobstensors

https://github.com/vllm-project/vllm/security/advisories/GHSA-rhcx-5729-88vg

https://euvd.enisa.europa.eu/vulnerability/EUVD-2026-109441

Details

Source: Mitre, NVD

Published: 2026-10-25

Updated: 2026-10-25

Risk Information

CVSS v2

Base Score: 6.8

Vector: CVSS2#AV:N/AC:L/Au:S/C:N/I:N/A:C

Severity: Medium

CVSS v3

Base Score: 7.7

Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H

Severity: High

CVSS v4

Base Score: 8.3

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H

Severity: High