CVE-2026-54232

描述

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.

如何修補 CVE-2026-54232

要修補 CVE-2026-54232,請將受影響套件升級到下列已修補版本。

• —升級至 0.22.1 或更新版本

CVE-2026-54232 正在被利用嗎?

低 — EPSS 為 0.3%,目前沒有觀察到大規模利用活動。

受影響套件(1)

• from 0, < 0.22.1

CVSS 分數

參考連結(1)

• EXPLOITgithub.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2