UTC
High

vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

CVE-2025-62372 · GHSA-pmqf-x6x8-p7qw · published 2025-11-20 · updated 2026-07-17

Severity
High
CVSS score
6.5
Chance of exploitation (EPSS)
0.41%
Fixed in
0.11.1
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Partial
  • CISA SSVC
What it is

Denial of service by crashing the engine

What to do

Upgrade vllm to 0.11.1 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/27204

If you cannot upgrade yet

Use API key to limit access to trusted users. Set --limit-mm-per-prompt to 0 for all non-text modalities to ban multimodal inputs, which includes multimodal embedding inputs. However, the model would then only accept text, defeating the purpose of using a multi-modal model.

Affected
PackageRegistryAffectedFixed in
vllmPyPI>= 0.5.5, < 0.11.10.11.1

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].