漏洞信息
尽管我们使用了先进的大模型技术,但其输出仍可能包含不准确或过时的信息。神龙努力确保数据的准确性,但请您根据实际情况进行核实和判断。
Vulnerability Title
Docker Model Runner container-to-host code execution via unsandboxed trust_remote_code in Python inference backends
Vulnerability Description
The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included in any model pulled from an OCI registry, resulting in arbitrary code execution on the Docker host as the Docker Desktop user when inference is triggered.
Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model and request inference.
CVSS Information
CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
Vulnerability Type
从非可信控制范围包含功能例程
Vulnerability Title
Docker Model Runner 安全漏洞
Vulnerability Description
Docker Model Runner是Docker开源的一个Docker模型运行器。 Docker Model Runner vllm-metal存在安全漏洞,该漏洞源于无条件设置trust_remote_code=True且无沙箱保护,可能导致加载模型分词器时执行任意Python文件,在触发推理时导致Docker主机上任意代码执行。
CVSS Information
N/A
Vulnerability Type
N/A