CVE-2026-114049

CVE-2026-114049CVE-2026-114049

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.

Scoring

CVSS 3.7 ()
VectorCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N
Last modified2026-10-21
Sourced from NVD. Curated for EU compliance use cases by Adam Lundqvist, Founder at SQUR.