CVSS 6.3 (medium) · published 2026-10-21
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 (NVD): vllm vllm
Fixed in (NVD): 0.31.0
Weakness: CWE-440
Source: NVD CVE-2026-114049
Connect an AI agent to the FixLane MCP server or ask the Telegram bot to check what you have installed against incidents with a verified fixed version.