CVE-2026-114049

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.31.0

Description A cross-request mask leak exists in the condense() function of the InputBatch class. This issue allows remote attackers to constrain the outputs of other clients by leaving stale allowed token ids rows. By submitting concurrent constrained generate requests, including through the unauthenticated '/invocations' endpoint, attackers can cause recycled batch slots to apply their token allowlist to the unrestricted requests of other users.

Recommendations Update vLLM to version 0.31.0 or later.