CVE-2026-54232
vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile
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.
INFO
Published Date :
June 22, 2026, 10:16 p.m.
Last Modified :
June 22, 2026, 10:16 p.m.
Remotely Exploit :
No
Source :
GitHub_M
Solution
- Update vLLM to version 0.22.1.
- Remove --extra-index-url pointing to custom indexes.
- Ensure package names are registered on PyPI.
- Disable unsafe-best-match index strategy.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-54232 vulnerability anywhere in the article.