CVE-2026-114049
Published:October 21, 2026
Updated:October 21, 2026
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.
Affected Packages
vllm (CONDA):
Affected version(s) >=0.8.3 <0.31.0Fix Suggestion:
Update to version 0.31.0https://github.com/vllm-project/vllm.git (GITHUB):
Affected version(s) >=v0.8.0 <v0.31.0Fix Suggestion:
Update to version v0.31.0vllm (PYTHON):
Affected version(s) >=0.8.0 <0.31.0Fix Suggestion:
Update to version 0.31.0Related Resources (2)
Do you need more information?
Contact UsCVSS v4
Base Score:
6.3
Attack Vector
NETWORK
Attack Complexity
HIGH
Attack Requirements
PRESENT
Privileges Required
NONE
User Interaction
NONE
Vulnerable System Confidentiality
NONE
Vulnerable System Integrity
LOW
Vulnerable System Availability
NONE
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
3.7
Attack Vector
NETWORK
Attack Complexity
HIGH
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
LOW
Availability
NONE
Weakness Type (CWE)
Expected Behavior Violation
EPSS
Base Score:
0.27