Low severity · published Oct 21, 2026
CVE-2026-114049
vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense
3.7
CVSS
0.3%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N
Attack vector
Network
Complexity
High
Privileges
None
User interaction
None
Confidentiality
None
Integrity
Low
Availability
None
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.3% · higher than 18% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
vllm · vllm-project
before 0.31.0 · source: vendor
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-114049
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-114049
github.com
https://github.com/vllm-project/vllm/security/advisories/GHSA-6cxc-2vcg-w5qc
www.vulncheck.com
https://www.vulncheck.com/advisories/vllm-before-0.31.0-stale-allowed-token-ids-mask-via-inputbatch-condense
More from vllm
9.8
CVE-2026-115915
vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
9.8
CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
9.8
CVE-2024-9053
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints