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.
https://github.com/vllm-project/vllm/security/advisories/GHSA-6cxc-2vcg-w5qc
Published: 2026-10-21
Updated: 2026-10-28
Base Score: 2.6
Vector: CVSS2#AV:N/AC:H/Au:N/C:N/I:P/A:N
Severity: Low
Base Score: 3.7
Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N
Severity: Low
Base Score: 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
Severity: Medium
EPSS: 0.00265