CVE-2026-54232
HIGH
MEDIUM
Priority: 0.05
BB Relevance:
68/100
Published: 2026-06-22
Modified: 2026-10-25
First seen: 2026-10-29
Status: active
Attack Surface
Network
Low Complexity
No Auth
Conf. Impact
Integ. Impact
CVSS Vector Breakdown
AV:
Network
AC:
Low
PR:
None
UI:
Required
S:
Unchanged
C:
High
I:
High
A:
High
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.
Weakness Classification (1)
References & Advisories (1)
Exploit
Third Party Advisory