CVE-2026-54232

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.22.1

Description vLLM is an inference and serving engine for large language models. The Dockerfile is susceptible to a dependency confusion attack involving the flashinfer-jit-cache package. This occurs because the package is retrieved from a custom index using --extra-index-url while the UV INDEX STRATEGY variable is set to unsafe-best-match and the package name was not registered on PyPI. A malicious actor could register the flashinfer-jit-cache package on PyPI to execute arbitrary code as root during the Docker build process. This could lead to the backdooring of container images, allowing the exfiltration of API credentials, user prompts, and model data from production deployments.

Recommendations Update to version 0.22.1.