CVE-2026-54232

8.8 HIGH 0.6% exploit odds Fix listed Code execution Library

What it is

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.

At a glance

Exploitability: Can be exploited over the network without logging in, but needs a user to act. High risk of data exposure, data tampering, service disruption.
Exploit odds: 0.6% chance of exploitation in the next 30 days (EPSS).
Fix: A patch, advisory or fixed version is referenced. Upgrade or apply it.