UTC
Medium

vLLM denial of service via outlines unbounded cache on disk

CVE-2025-29770 · GHSA-mgrm-fgjv-mhv8 · published 2025-03-19 · updated 2026-06-08

Severity
Medium
CVSS score
6.5
Chance of exploitation (EPSS)
0.47%
Fixed in
0.8.0
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Partial
  • CISA SSVC
What it is

The outlines library is one of the backends used by vLLM to support structured output (a.k.a. guided decoding). Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has been on by default in vLLM. Outlines is also available by default through the OpenAI compatible API server. The affected code in vLLM is vllm/modelexecutor/guideddecoding/outlineslogitsprocessors.py, which unconditionally uses the cache from outlines. vLLM should have this off by default and allow administrators to opt-in due to the potential for abuse.

What to do

Upgrade vllm to 0.8.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.

https://github.com/vllm-project/vllm/pull/14837 The fix is to disable this cache by default since it does not provide an option to limit its size. If you want to use this cache anyway, you may set the VLLMV0USEOUTLINESCACHE environment variable to 1.

If you cannot upgrade yet

There is no way to workaround this issue in existing versions of vLLM other than preventing untrusted access to the OpenAI compatible API server.

Affected
PackageRegistryAffectedFixed in
vllmPyPI< 0.8.00.8.0

The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].