CVE-2026-114049

Published: Ott 21, 2026 Last Modified: Ott 21, 2026
ExploitDB:
Other exploit source:
Google Dorks:
MEDIUM 6,3
Source: [email protected]
Attack Vector: network
Attack Complexity: high
Privileges Required: none
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A
LOW 3,7
Source: [email protected]
Attack Vector: network
Attack Complexity: high
Privileges Required: none
User Interaction: none
Scope: unchanged
Confidentiality: none
Integrity: low
Availability: none

Description

AI Translation Available

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.

440

Expected Behavior Violation

Draft
Abstraction: Base Structure: Simple
Common Consequences
Security Scopes Affected:
Other
Potential Impacts:
Quality Degradation Varies By Context
Applicable Platforms
Technologies: ICS/OT
View CWE Details
https://github.com/vllm-project/vllm/security/advisories/GH…
https://github.com/vllm-project/vllm/security/advisories/GHSA-6cxc-2vcg-w5qc
https://www.vulncheck.com/advisories/vllm-before-0.31.0-sta…
https://www.vulncheck.com/advisories/vllm-before-0.31.0-stale-allowed-token-ids…