Vulnerability 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 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 Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | < 0.11.1 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838dPatch
- https://github.com/vllm-project/vllm/pull/28126Issue Tracking
- https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gmVendor Advisory
FAQ
What is CVE-2025-66448?
CVE-2025-66448 is a vulnerability with a CVSS score of 7.1 (HIGH). 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 l...
How severe is CVE-2025-66448?
CVE-2025-66448 has been rated HIGH with a CVSS base score of 7.1/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2025-66448?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.