UpHeron
All vulnerabilities

Servers and applications

CVE-2025-66448

Remote code execution via transformers_utils/get_config

Severity
High 8.8
Published
1 Dec 2025
Last changed
18 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.11.1
Also known as
GHSA-8fr4-5q9j-m8gm
Sources
NVD, Project advisories (GitHub)

Description

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and…

Affected software

SoftwareAffected versions
vLLMServers and applications · cpe:a:vllm:vllm
  • Every version before 0.11.1
vLLMServers and applications · github:vllm-project/vllm
  • Every version before 0.11.1

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2025-66448
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2025-66448
  • GitHub Advisory Database https://github.com/advisories/GHSA-8fr4-5q9j-m8gm
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm