CVE-2026-54232

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.
References
Configurations

Configuration 1 (hide)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

History

24 Jun 2026, 16:51

Type Values Removed Values Added
CPE cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
First Time Vllm
Vllm vllm
References () https://github.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2 - () https://github.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2 - Exploit, Third Party Advisory

22 Jun 2026, 23:16

Type Values Removed Values Added
New CVE

Information

Published : 2026-06-22 23:16

Updated : 2026-06-24 16:51


NVD link : CVE-2026-54232

Mitre link : CVE-2026-54232

CVE.ORG link : CVE-2026-54232


JSON object : View

Products Affected

vllm

  • vllm
CWE
CWE-427

Uncontrolled Search Path Element