Vulnerability · Published Oct 21, 2026 · Assigned by VulnCheck

CVE-2026-114049vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense

Low 3.7

In plain English

A low-severity security flaw in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 19% of all known vulnerabilities).

Severity (CVSS 3.1)3.7Low

Exploit odds (30 days)0.3%top 81.5% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected products (as reported)

Vendor	Product	Versions
vllm-project	vllm	0 – before 0.31.0

Weakness: CWE-440 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N

References

GitHub Security Advisory (GHSA-6cxc-2vcg-w5qc) vendor-advisory
VulnCheck Advisory: vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense third-party-advisory