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

Advisory record · `GHSA-h3rc-6mm3-gc2m`

- **Identifiers:** `GHSA-h3rc-6mm3-gc2m` · `CVE-2026-114053`
- **State:** Confirmed
- **Severity:** CVSS 9.2 Critical
- **Critical:** Yes: CVSS 9+
- **Weakness (CWE):** [CWE-94](https://cwe.mitre.org/data/definitions/94.html) · [CWE-829](https://cwe.mitre.org/data/definitions/829.html)
- **Tags:** [Code injection](https://agentprime.io/advisories/tag/code-injection.md) · [CWE-829](https://agentprime.io/advisories/tag/cwe-829.md)
- **Published:** 27 Oct 2026
- **Updated:** 27 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 27 Oct 2026, 15:36 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Critical

Critical, because:

- CVSS score 9.2: 9.0 or more.

How we decide what’s critical: <https://agentprime.io/advisories/critical.md>

## Affected packages

- `vllm` (PyPI): affected `>=0.7.3, <0.31.0`; fixed in `0.31.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> vLLM versions 0.7.3 up to, but not including, 0.31.0 let a request's mm_processor_kwargs.code_revision select a different revision of a model's processor code when trust_remote_code is enabled. An attacker who controls a revision in the served model repository and can send multimodal requests could execute arbitrary code in the vLLM API process. Upgrade to vLLM 0.31.0 or later.

Written 31 Oct 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 9.2 Critical, CVSS 4.0: `CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N`, from CNA (VulnCheck)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0046, the 40th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 21 Oct 2026, 01:17 UTC: [Confirmed by NVD](https://nvd.nist.gov/vuln/detail/CVE-2026-114053)
- 31 Oct 2026, 14:07 UTC: First seen by agentprime
- 31 Oct 2026, 14:07 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-h3rc-6mm3-gc2m)

## Sources

- [GitHub Advisory Database: GHSA-h3rc-6mm3-gc2m](https://github.com/advisories/GHSA-h3rc-6mm3-gc2m)
- [OSV: GHSA-h3rc-6mm3-gc2m](https://osv.dev/vulnerability/GHSA-h3rc-6mm3-gc2m)
- <https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-6mm3-gc2m>
- <https://github.com/vllm-project/vllm/pull/58830>
- <https://github.com/vllm-project/vllm/commit/31f2e70cd3e403aaa471fb7fe3d33a7207aaf3cc>
- <https://github.com/vllm-project/vllm>
- <https://github.com/vllm-project/vllm/releases/tag/v0.31.0>
- <https://nvd.nist.gov/vuln/detail/cve-2026-114053>
- <https://www.vulncheck.com/advisories/vllm-0.7.3-before-0.31.0-rce-via-mm-processor-kwargs-code-revision>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-h3rc-6mm3-gc2m>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-h3rc-6mm3-gc2m/>. Everything for agents: <https://agentprime.io/llms.txt>.