CVE-2025-66448

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 executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.

CVSS 3.1

8.8CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

EPSS

0.7% chance of exploitation in the next 30 days; higher than 51% of CVEs (scores of 2026-10-25)

CWE

CWE-94

Published

2025-12-01

Modified

2026-10-18

Record from

the NVD, synced 2026-10-19

Affected

• vllm:vllm

Packages (OSV)

References

• https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86
• https://github.com/vllm-project/vllm/pull/28126
• https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm

Check your stackJSON