CVE-2026-22807: vLLM affected by RCE via auto_map dynamic module loading during model initialization

Published Jan 21, 2026
·
Updated

Summary

vLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path to execute at server startup.

---

Impact

An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access.

---

Affected Versions

All versions where vllm/modelexecutor/models/registry.py resolves automap entries with trygetclassfromdynamicmodule without checking trustremotecode (at least current main).

---

Details

During model resolution, vLLM unconditionally iterates automap entries from the model config and calls trygetclassfromdynamicmodule, which delegates to Transformers’ getclassfromdynamicmodule and executes the module code.

This occurs even when trustremotecode is false, allowing a malicious model repo to embed code in a referenced module and have it executed during initialization.

Relevant code

- vllm/modelexecutor/models/registry.py:856 — automap resolution - vllm/transformersutils/dynamicmodule.py:13 — delegates to getclassfromdynamicmodule, which executes code

---

Fixes

https://github.com/vllm-project/vllm/pull/32194

Credits

Reported by bugbunny.ai

Other sources

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face automap dynamic modules during model resolution without gating on trustremotecode, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.

MITRE

Affected Software

2 affected componentsFixes available
pip/vllm>=0.10.1<0.14.0
0.14.0
vllm vllm>=0.10.1<0.14.0

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade pip/vllm to a version that resolves this vulnerability.

    Fixed in 0.14.0
  2. Upgrade

    Upgrade vllm to a version that resolves this vulnerability.

    Fixed in 0.14.0
  3. Compensating control

    Ensure model loading uses a model repo/path you control (or otherwise disallow attacker-influenced local directories and remote Hugging Face repos) because vLLM can execute attacker-controlled Python code embedded in referenced auto_map dynamic modules during model initialization.

Event History

Jan 21, 2026
Advisory Published
via GitHub·04:12 PM
Data Sourced
via GitHub·04:12 PM
DescriptionSeverityWeaknessAffected Software
CVE Published
via MITRE·09:13 PM
Data Sourced
via MITRE·09:13 PM
DescriptionSeverityWeakness
Data Sourced
via Red Hat·10:01 PM
DescriptionSeverityAffected Software
Data Sourced
via NVD·10:15 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·10:15 PM
RemedyAffected Software
Free Weekly Intel

Don't miss critical vulnerabilities

Join thousands of security professionals who receive our weekly digest of trending CVEs, zero-days, and exploited vulnerabilities.

No spam. Unsubscribe anytime.

Frequently Asked Questions

1

What is the severity of CVE-2026-22807?

CVE-2026-22807 has been rated as high severity due to its potential for remote code execution.

2

How do I fix CVE-2026-22807?

To mitigate CVE-2026-22807, update vLLM to version 0.14.0 or later which addresses the vulnerability by ensuring proper trust gating.

3

Who is affected by CVE-2026-22807?

Users of vLLM versions between 0.10.1 and 0.14.0 are affected by CVE-2026-22807.

4

What impact does CVE-2026-22807 pose?

CVE-2026-22807 allows attacker-controlled Python code to execute on the server, which can lead to data breaches and server compromises.

5

When was CVE-2026-22807 disclosed?

CVE-2026-22807 was disclosed as a security vulnerability in 2026.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203