CVE-2026-114049vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense
Updated under an hour ago ()
Does this affect you?
It affects vllm-project vllm. Add what you run to find out whether that includes you.
No exploitation reported and no EPSS estimate yet.
Do this next
Free account, 1 product
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.
- CVSS
- 3.7 LOW (v3.1, CNA)CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N
- Weakness (CWE)
- CWE-440
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- Not loaded for this CVE
- Assigned by
- VulnCheck
- NVD analysis
- Received
- Record last updated
- Oct 21, 2026
- First seen by InfoSec Signals
- Oct 21, 2026
Affected products
vllm-project vllm vllm_project:vllm (from the name) | before 0.31.0; 0.31.0 not affected | CNA record |
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-6cxc-2vcg-w5qcvendor-advisory
- https://www.vulncheck.com/advisories/vllm-before-0.31.0-stale-allowed-token-ids-mask-via-inputbatch-condensethird-party-advisory
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.