# CVE-2025-66448: vLLM remote code execution in Nemotron_Nano_VL_Config via auto_map

Source: https://junglewise.ai/threats/cve-2025-66448-vllm-remote-code-execution-in-nemotron-nano-vl-config-via-auto  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2025-12-01. Updated: 2026-07-17  
License: CC BY 4.0 with a link back

CVE-2025-66448 · Severity: high · CVSS 7.1 · Published 2025-12-01

vLLM, a library used for serving and deploying large language models, is vulnerable to a security flaw that allows for remote code execution. An attacker can create a malicious model configuration that, when loaded by a user or automated system, silently executes arbitrary code on the host machine. This occurs even if the user has explicitly disabled the setting to trust remote code, potentially leading to full system compromise or data theft.

Technologies: [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm), [Vllm](https://junglewise.ai/threats/technologies/vllm). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi), [Vllm](https://junglewise.ai/threats/vendors/vllm).

## Quick answers

**Is CVE-2025-66448 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2025-66448 being exploited in the wild.

**How severe is CVE-2025-66448?** High severity, with a CVSS score of 7.1, published 1 December 2025.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0,fixed=0.11.1.

**Is there a fix for CVE-2025-66448?** Yes. vllm (PyPI): upgrade to 0.11.1 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2025-66448 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2025-66448?** Check whether you run vllm (PyPI) 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 0.11.1 or later

  ```sh
  pip install "vllm>=0.11.1"
  ```


## Technical details

A remote code execution (RCE) vulnerability exists in vLLM's 'Nemotron_Nano_VL_Config' class within 'transformers_utils/get_config'. The vulnerability is caused by the improper handling of 'auto_map' entries in model configurations, which are resolved using 'get_class_from_dynamic_module' and immediately instantiated. This process fetches and executes Python code from remote repositories without enforcing the 'trust_remote_code' safety flag. An attacker can exploit this by providing a malicious model configuration that points to a remote repository containing arbitrary code. The vulnerability is patched in version 0.11.1.

## Affected products

- vllm-project vllm < 0.11.1

## Identifiers

- CVE-2025-66448
- GHSA-8fr4-5q9j-m8gm
- PYSEC-2026-2015

## Timeline

- 2025-12-01: advisory: NVD publication date
- 2025-12-02: disclosed: GitHub Advisory published
- 2025-12-02: patched: GitHub Advisory marked as reviewed and patched version identified

## References

- [https://api.github.com/users/Vancir](https://api.github.com/users/Vancir)
- [https://github.com/Vancir](https://github.com/Vancir)
- [https://api.github.com/users/Vancir/gists%7B/gist_id%7D](https://api.github.com/users/Vancir/gists%7B/gist_id%7D)
- [https://api.github.com/users/Vancir/repos](https://api.github.com/users/Vancir/repos)
- [https://avatars.githubusercontent.com/u/19147918?v=4](https://avatars.githubusercontent.com/u/19147918?v=4)
- [https://api.github.com/users/Vancir/events%7B/privacy%7D](https://api.github.com/users/Vancir/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)