Vulnerability 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.
CVSS Score
LOW
Related Weaknesses (CWE)
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-
FAQ
What is CVE-2026-114049?
CVE-2026-114049 is a vulnerability with a CVSS score of 3.7 (LOW). 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 s...
How severe is CVE-2026-114049?
CVE-2026-114049 has been rated LOW with a CVSS base score of 3.7/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-114049?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.