UTC
High

vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution

CVE-2026-114053 · GHSA-h3rc-6mm3-gc2m · published 2026-10-27

Severity
High
CVSS score
8.1
Chance of exploitation (EPSS)
0.46%
Fixed in
0.31.0
  • Exploitation No known exploitation
  • Automatable No
  • Technical impact Total
  • CISA SSVC
What it is

An untrusted multimodal request can set mmprocessorkwargs.coderevision. When vLLM serves a model whose Hugging Face processor uses dynamic automap code and the operator enabled --trust-remote-code, this request value reaches AutoProcessor.from_pretrained and selects the Python revision imported by Transformers. This lets a client replace the operator-reviewed processor module with code from another revision of the same model repository. The operator-selected model/data revision remains pinned; only the executed processor code changes. Importing a Python module is arbitrary code execution in the vLLM API/renderer process.

What to do

Upgrade vllm to 0.31.0 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.

1. Separate processor-construction arguments from untrusted processor-call arguments. An allowlist of supported request-time preprocessing controls is safest. 2. Reject coderevision and other loader/source controls in request mmprocessorkwargs, and pass modelconfig.code_revision explicitly as the only permitted processor-code revision. 3. Add a regression test proving a request cannot change the loaded module revision while operator pins remain effective. 4. Protect /tokenize with the configured authentication policy as defense in depth. Expected safe behavior is either a 4xx response for reserved request keys or silently ignoring them before processor construction.

Affected
PackageRegistryAffectedFixed in
vllmPyPI>= 0.7.3, < 0.31.00.31.0

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].