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
vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile
Vulnerability Description
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY="unsafe-best-match" is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Vulnerability Type
对搜索路径元素未加控制
Vulnerability Title
vLLM 权限许可和访问控制问题漏洞
Vulnerability Description
vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.22.1之前版本存在权限许可和访问控制问题漏洞,该漏洞源于通过flashinfer-jit-cache包的依赖混淆攻击,可能导致攻击者在Docker构建过程中以root权限执行任意代码并植入后门,从而泄露用户提示、API凭证和模型数据。
CVSS Information
N/A
Vulnerability Type
N/A