CVE-2026-114049
vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense
- State
- Published
- Severity
- 6.3 Medium
- Published
- Oct 21, 2026
- Updated
- Oct 28, 2026
- Reserved
- Oct 20, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 6.3 Medium | 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 | VulnCheck |
| 3.1 | 3.7 Low | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N | VulnCheck |
Weaknesses
- CWE-440 Expected Behavior Violation
Affected Products
| Product | Versions |
|---|---|
vllmvllm-project |
|
References
- GitHub Security Advisory (GHSA-6cxc-2vcg-w5qc)vendor-advisory
- VulnCheck Advisory: vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condensethird-party-advisory
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.