CVE-2026-114049 PUBLISHED

vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense

Assigner: VulnCheck
Reserved: 20.10.2026 Published: 21.10.2026 Updated: 21.10.2026

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.

CVSS Vector: 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
CVSS Score: 6.3

Exploitability Metrics		Vulnerable System Impact Metrics		Subsequent System Impact Metrics
Attack Vector	Network	Confidentiality	None	Confidentiality	None
Attack Complexity	High	Integrity	Low	Integrity	None
Attack Requirements	Present	Availability	None	Availability	None
Privileges Required	None
User Interaction	None

CVSS 4.0

CVSS Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N
CVSS Score: 3.7

Attack Vector	Network	Scope	Unchanged
Attack Complexity	High	Confidentiality Impact	None
Privileges Required	None	Integrity Impact	Low
User Interaction	None	Availability Impact	None

CVSS 3.1

Product Status

Vendor	vllm-project
Product	vllm
Versions	Default: unaffected affected from 0 to 0.31.0 (excl.) Version 0.31.0 is unaffected

CVE-2026-114049 PUBLISHED

vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense

Metrics

Product Status

Credits

References

Problem Types