CVE-2025-66448

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.

Details

The vulnerable code resolves and instantiates classes from auto_map entries without checking whether those entries point to a different repo or whether remote code execution is allowed.

class Nemotron_Nano_VL_Config(PretrainedConfig):
    model_type = 'Llama_Nemotron_Nano_VL'

    def __init__(self, **kwargs):
        super().__init__(**kwargs)

        if vision_config is not None:
            assert "auto_map" in vision_config and "AutoConfig" in vision_config["auto_map"]
            # <-- vulnerable dynamic resolution + instantiation happens here
            vision_auto_config = get_class_from_dynamic_module(*vision_config["auto_map"]["AutoConfig"].split("--")[::-1])
            self.vision_config = vision_auto_config(**vision_config)
        else:
            self.vision_config = PretrainedConfig()

get_class_from_dynamic_module(...) is capable of fetching and importing code from the Hugging Face repo specified in the mapping. trust_remote_code is not enforced for this code path. As a result, a frontend repo can redirect the loader to any backend repo and cause code execution, bypassing the trust_remote_code guard.

Fixes

• https://github.com/vllm-project/vllm/pull/28126

This is a critical vulnerability because it breaks the documented trust_remote_code safety boundary in a core model-loading utility. The vulnerable code lives in a common loading path, so any application, service, CI job, or developer machine that uses vllm’s transformer utilities to load configs can be affected. The attack requires only two repos and no user interaction beyond loading the frontend model. A successful exploit can execute arbitrary commands on the host.

Untrusted input is evaluated as executable code within the application's runtime environment. Typical impact: arbitrary code execution within the application's privilege context.

CVE-2025-66448 has a CVSS score of 7.1 (High). The vector is network-reachable, low privileges required, and user interaction required. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.11.1); upgrading removes the vulnerable code path.

Kodem intelligence

1. What is CVE-2025-66448? CVE-2025-66448 is a high-severity code injection vulnerability in vllm (pip), affecting versions < 0.11.1. It is fixed in 0.11.1. Untrusted input is evaluated as executable code within the application's runtime environment.
2. How severe is CVE-2025-66448? CVE-2025-66448 has a CVSS score of 7.1 (High). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
3. Which versions of vllm are affected by CVE-2025-66448? vllm (pip) versions < 0.11.1 is affected.
4. Is there a fix for CVE-2025-66448? Yes. CVE-2025-66448 is fixed in 0.11.1. Upgrade to this version or later.
5. Is CVE-2025-66448 exploitable, and should I be worried? Whether CVE-2025-66448 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
6. What actually determines whether CVE-2025-66448 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
7. How do I fix CVE-2025-66448? Upgrade vllm to 0.11.1 or later.