What’s Vulnerable › Vulnerabilities

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

• Severity: low (CVSS 3.7 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.3% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-10-21 · updated 2026-10-28
• Weakness: CWE-440

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

• vllm-project vllm: before 0.31.0 — fixed in 0.31.0

How to fix

Upgrade to a fixed version: vllm-project vllm 0.31.0. Check the vendor advisory for mitigations.

References

• https://github.com/vllm-project/vllm/security/advisories/GHSA-6cxc-2vcg-w5qc
• https://www.vulncheck.com/advisories/vllm-before-0.31.0-stale-allowed-token-ids-mask-via-inputbatch-condense

Get alerted when CVE-2026-114049 or the next vulnerability affects your stack