Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1325 CNY

100%

CVE-2026-54232— vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile

CVSS 8.8 · High EPSS 0.30% · P22
Get alerts for future matching vulnerabilitiesLog in to subscribe

I. Basic Information for CVE-2026-54232

Vulnerability Information

Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile
Source: NVD (National Vulnerability Database)
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.
Source: NVD (National Vulnerability Database)
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Source: NVD (National Vulnerability Database)
Vulnerability Type
对搜索路径元素未加控制
Source: NVD (National Vulnerability Database)

Affected Products

VendorProductAffected VersionsCPESubscribe
vllm-projectvllm < 0.22.1 -

II. Public POCs for CVE-2026-54232

#POC DescriptionSource LinkShenlong Link
AI-Generated POCPremium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-54232

登录查看更多情报信息。

Other References for CVE-2026-54232 (1)

Same Patch Batch · vllm-project · 2026-06-22 · 8 CVEs total

CVE-2026-487469.1 CRITICALvLLM: OpenAI auth bypass
CVE-2026-415237.5 HIGHvLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arb
CVE-2026-471556.5 MEDIUMvLLM: Artifact Pin Decay in vLLM allows pinned deployments to load unpinned code, weights,
CVE-2026-542336.5 MEDIUMvLLM: OOM Denial of Service via Audio Decompression Bomb
CVE-2026-542365.3 MEDIUMvLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
CVE-2026-53923vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overfl
CVE-2026-54235vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kern

IV. Related Vulnerabilities

V. Comments for CVE-2026-54232

No comments yet


Leave a comment