CVE-2026-54232

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.

Severity
HIGH
CVSS v3
8.8
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H · source cna
Exploit chance (EPSS)
0.563%
chance of exploitation in the next 30 days
higher than 47.4% of scored CVEs · 2026-11-17
CISA KEV
Not listed
Public exploit code
Yes
Exploit references (NVD and CNA): 1
Metasploit modules: 0
Nuclei templates: 0

Weakness

CISA SSVC decision points

Exploitationnone
Automatableno
Technical impacttotal
Scored2026-06-23

Timeline

  1. 2026-06-22Published by the CNA22:16 UTC
  2. 2026-06-23CISA SSVC decision recorded1 day after publication

The timeline shows what already happened. To be told when this CVE changes next, watch it from the API.

Affected products

Products listed as vulnerable. Upgrade to the version under "Fixed in", or a later one.

ProductVulnerable versionsFixed in
vllm vllmbefore 0.22.1fixed in 0.22.10.22.1

Products and versions as NVD and the vendor that published the CVE list them.

References

Get more CVE data from the API.

Free without a key or signup. Pro adds monitoring and higher limits: pricing.

Sources