CVE-2025-66448
Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.66%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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 3.1
- 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- EPSS
- 0.66% probability · 50th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-94
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.