# CVE-2026-22807: vLLM arbitrary code execution via auto_map dynamic module loading

Source: https://junglewise.ai/threats/cve-2026-22807-vllm-arbitrary-code-execution-via-auto-map-dynamic-module-loading  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-01-21. Updated: 2026-07-17  
License: CC BY 4.0 with a link back

CVE-2026-22807 · Severity: high · CVSS 8.8 · Published 2026-01-21

vLLM, a high-throughput engine for serving AI models, is vulnerable to a security flaw that allows for unauthorized code execution. By providing a specially crafted AI model repository, an attacker can force the server to run malicious Python code during the initial setup process. This occurs before the server even begins processing user requests and can lead to a full system compromise or data theft.

Technologies: [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm), [Red Hat AI Inference Server](https://junglewise.ai/threats/technologies/ai-inference-server), [Vllm](https://junglewise.ai/threats/technologies/vllm). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi), [Red Hat](https://junglewise.ai/threats/vendors/red-hat), [Vllm](https://junglewise.ai/threats/vendors/vllm).

## Quick answers

**Is CVE-2026-22807 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-22807 being exploited in the wild.

**How severe is CVE-2026-22807?** High severity, with a CVSS score of 8.8, published 21 January 2026.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0.10.1,fixed=0.14.0; Red Hat AI Inference Server 3.2, 3.3.

**Is there a fix for CVE-2026-22807?** Yes. vllm (PyPI): upgrade to 0.14.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-22807 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-22807?** Check whether you run vllm (PyPI), Red Hat AI Inference Server or Vllm at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- vllm (PyPI): upgrade to 0.14.0 or later

  ```sh
  pip install "vllm>=0.14.0"
  ```


## Technical details

A code injection vulnerability exists in vLLM's model resolution logic within `vllm/model_executor/models/registry.py`. The application unconditionally iterates through `auto_map` entries in a model's configuration and invokes `try_get_class_from_dynamic_module`, which eventually executes arbitrary Python code via the Transformers library. This execution occurs even if `trust_remote_code` is set to false. An attacker who can influence the model repository path (either locally or via a remote Hugging Face repo) can achieve arbitrary code execution on the host at server startup. The issue is fixed in version 0.14.0.

## Affected products

- vllm-project vllm >= 0.10.1, < 0.14.0

## Identifiers

- CVE-2026-22807
- GHSA-2pc9-4j83-qjmr
- PYSEC-2026-2010

## Timeline

- 2026-01-21: disclosed
- 2026-01-21: advisory
- 2026-01-21: patched: Fixed in version 0.14.0

## References

- [https://api.github.com/users/zaddy6](https://api.github.com/users/zaddy6)
- [https://github.com/zaddy6](https://github.com/zaddy6)
- [https://api.github.com/users/zaddy6/gists%7B/gist_id%7D](https://api.github.com/users/zaddy6/gists%7B/gist_id%7D)
- [https://api.github.com/users/zaddy6/repos](https://api.github.com/users/zaddy6/repos)
- [https://avatars.githubusercontent.com/u/49834299?v=4](https://avatars.githubusercontent.com/u/49834299?v=4)
- [https://api.github.com/users/zaddy6/events%7B/privacy%7D](https://api.github.com/users/zaddy6/events%7B/privacy%7D)

## Related threats

- [vLLM chat template resource exhaustion DoS](https://junglewise.ai/threats/cve-2026-115918-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server](https://junglewise.ai/threats/cve-2026-115917-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM off-by-one error in tokenizer max_token_id validation](https://junglewise.ai/threats/cve-2026-115916-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM image format validation bypass in media processing](https://junglewise.ai/threats/cve-2026-115915-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM denial of service in DeepSeek-OCR image processing](https://junglewise.ai/threats/cve-2026-115914-vllm-is-an-inference-and-serving-engine-for-large-language)