UTC
Medium

vLLM Unauthenticated Requests Exploit DeepStream Backend Confusion for DoS

CVE-2026-78684 · GHSA-cqm8-jxg6-fqfq · published 2026-08-11 · updated 2026-09-01

Severity
Medium
CVSS score
5.3
Chance of exploitation (EPSS)
Not scored
Fixed in
0.27.0
  • Exploitation No known exploitation
  • Automatable Yes
  • Technical impact Partial
  • CISA SSVC
What it is

This is a CWE-400 resource-consumption and partial denial-of-service vulnerability caused by GPU backend identity confusion and inconsistent enforcement of resource controls. An unauthenticated remote client can: activate DeepStream/NVDEC without startup configuration or GPU-memory reservation; choose the initial size of the process-wide DecodePool; bypass VLLM_MAX_IMAGE_PIXELS for DeepStream video requests; and degrade availability for unrelated requests through concurrent GPU video workloads. The demonstrated impact is partial and recoverable availability loss. …

What to do

Upgrade vllm to 0.27.0 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.

Register deepstream as a GPU-backed codec and apply the same GPU classification to loader and codec selection. Reject request-level DeepStream selection unless it was statically configured and included in startup GPU-memory reservation. Fail closed for unknown request-level backend names. Call _check_frame_pixel_limit(width, height) immediately after probe_metadata(). Make pool_size startup-only rather than request-controlled. Add a total decoded-work limit based on selected frames × width × height. Add regression tests for request-level DeepStream selection and OpenCV/DeepStream pixel-limit parity.

Affected
PackageRegistryAffectedFixed in
vllmPyPI< 0.27.00.27.0

The impact, patch and workaround text comes from the advisory, shortened (published by vLLM). 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].