PT-2026-51418 · Vllm · Vllm
Jstawinski
·
Published
2026-06-22
·
Updated
2026-06-22
·
CVE-2026-54232
CVSS v3.1
8.8
High
| Vector | AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
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.
Fix
Uncontrolled Search Path Element
Found an issue in the description? Have something to add? Feel free to write us 👾
Weakness Enumeration
Related Identifiers
Affected Products
Vllm