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

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

8.1 · CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS

• CVE-2026-114053: 0.46% estimated exploitation activity in the next 30 days; percentile 40.06 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary An untrusted multimodal request can set `mm_processor_kwargs.code_revision`. When vLLM serves a model whose Hugging Face processor uses dynamic `auto_map` 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. The PoC below demonstrates this with an import-time filesystem write. It is fully offline and does not require a GPU, model weights, or changes to a real Hub repository.

Affected snapshot - Repository: `vllm-project/vllm` - Verified commit:…

Published by the source

27 Oct 2026, 15:36 UTC

Last modified by the source

27 Oct 2026, 15:47 UTC

Source last checked

28 Oct 2026, 06:10 UTC

1. Revision 2 · amended · 28 Oct 2026

   Amended from osv record GHSA-h3rc-6mm3-gc2m

2. Revision 1 · created · 27 Oct 2026

   Published from ghsa record GHSA-h3rc-6mm3-gc2m

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-114053

Advisory: vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution
IDs: CVE-2026-114053, GHSA-h3rc-6mm3-gc2m
Record: https://patchnext.com/advisories/cve-2026-114053 (revision 2, source checked 28 Oct 2026, 06:10 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: High (CVSS 8.1)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: vllm 0.31.0. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI vllm: affected >= 0.7.3, < 0.31.0; fixed in 0.31.0

## Suggested inspection (read-only)
- `python -m pip show vllm`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on vllm.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-h3rc-6mm3-gc2m (OSV record GHSA-h3rc-6mm3-gc2m lists affected ranges: PyPI vllm >=0.7.3 <0.31.0 (fixed))
- Verified: https://github.com/advisories/GHSA-h3rc-6mm3-gc2m (GitHub-reviewed advisory GHSA-h3rc-6mm3-gc2m lists affected ranges: PyPI vllm >=0.7.3 <0.31.0)

Commands are suggestions: review each one before running it.