CVE-2026-114049
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.
- Score
- CVSS 4.0 6.3 Medium
- Status
- Undergoing Analysis - disclosure@vulncheck.com
- Published
- 2026-10-21
- Last modified
- 2026-10-28
- Weaknesses
- CWE-440
Affected products
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6cxc-2vcg-w5qc
- https://www.vulncheck.com/advisories/vllm-before-0.31.0-stale-allowed-token-ids-mask-via-inputbatch-condense
