---
id: "CVE-2026-114049"
kind: "vulnerability"
aliases: ["CVE-2026-114049"]
title: "vLLM: stale token allowlists leak between concurrent requests, constraining other users' outputs"
severity: "medium"
cvss: 6.3
epss: 0.00265
exploited: false
status: "open"
category: "ai-tooling"
products: []
ecosystems: []
tags: ["ai-tooling", "llm-serving", "python", "self-hosted", "vllm"]
not_affected_if: ["auth-required", "no-constrained-generation", "single-tenant-deployment"]
published_at: "2026-10-21T01:17:27+00:00"
first_seen_at: "2026-10-23T21:57:27+00:00"
updated_at: "2026-10-25T04:01:25+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-114049", "first_seen_at": "2026-10-23T21:57:27+00:00"}, {"source": "epss", "url": "https://api.first.org/data/v1/epss?cve=CVE-2026-114049", "first_seen_at": "2026-10-24T13:15:55+00:00"}]
---

# vLLM: stale token allowlists leak between concurrent requests, constraining other users' outputs

vLLM before 0.31.0 fails to clear per-request allowed_token_ids masks when batch slots are recycled in InputBatch.condense(). A remote attacker can make other clients' unrestricted generation requests inherit a token allowlist, constraining their outputs.

_Summary, check and fix written by a model from the sources; labelled as such._

## How to check

- Check the installed vLLM version with `pip show vllm` or `python -c "import vllm; print(vllm.__version__)"`
- Check whether the server is reachable on an /invocations endpoint without authentication, which the sources say is exploitable

## Fix

- Upgrade vLLM to `0.31.0` or later
- Until upgraded, restrict access to the /invocations endpoint behind authentication

## Timeline

- 2026-10-23T21:57:27+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-114049
- 2026-10-24T13:15:55+00:00 epss https://api.first.org/data/v1/epss?cve=CVE-2026-114049

## From the sources

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.

---

_Free to read at a human pace. An API with keys and an MCP server are in preparation; early access: hello@infrastack.ai_