CVE-2026-114049

Published: Oct 21, 2026Modified: Oct 22, 2026

6.3

Vector

CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XShow less

Source: disclosure@vulncheck.com (Secondary)

Description

vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycled batch slots apply their token allowlist to victims' unrestricted requests.

Related CWEs

CWE-440

Expected Behavior Violation

A feature, API, or function does not perform according to its specification.

References (2)

https://github.com/vllm-project/vllm/security/advisories/GHSA-6cxc-2vcg-w5qc

Source: disclosure@vulncheck.com

https://www.vulncheck.com/advisories/vllm-before-0.31.0-stale-allowed-token-ids-mask-via-inputbatch-condense

Source: disclosure@vulncheck.com

Timeline

No history available yet.