UTC
Medium

vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

CVE-2026-73560 · GHSA-4hhp-h66f-j5j7 · published 2026-09-08

Severity
Medium
CVSS score
6.5
Chance of exploitation (EPSS)
0.41%
Fixed in
0.26.0
  • Exploitation Public proof of concept
  • Automatable No
  • Technical impact Partial
  • CISA SSVC
What it is

1. SSRF — internal-network probing / cloud-metadata theft. Standard requests.get follows redirects and accepts any URL. An attacker who controls a multimodaldata value can: read AWS / GCP / Azure instance metadata (e.g. ), probe internal services on the vLLM host (http://127.0.0.1: , http://10.x.y.z), exfiltrate via DNS / HTTP timing oracles even when the body is rejected by Image.open. 2. Arbitrary local file read via file://path (line 242) and the unguarded fallback Image.open(src) (line 248). Any file readable by the vLLM process is reachable through the model pipeline; with suitable formats this exposes /etc/passwd, ~/.aws/credentials, etc. 3.

What to do

Upgrade vllm to 0.26.0 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.

Replace direct requests.get and bare Image.open paths with MediaConnector.fetchimage / fetchaudio_async (or pass the inputs through MediaConnector before they reach the processor):

Affected
PackageRegistryAffectedFixed in
vllmPyPI< 0.26.00.26.0

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].