Skip to content
Fencer Vulns
high 8.8

CVE-2026-54232 json

vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile

published 2026-06-22 4 mo ago modified 2026-10-25 14 d ago also GHSA-jrf6-vqxq-pjv2 , PYSEC-2026-227 , EUVD-2026-38405

cvss
8.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.6%
EPSS 0.6% chance of exploitation in 30 days, percentile 47%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi vllm 0.22.1
  • vllm vllm 0.22.1

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-54232 updated cvss 5.7

vllm: flashinfer-jit-cache: vLLM: Arbitrary code execution via dependency confusion during Docker build

  • Red Hat AI Inference Server rhaii/vllm-cuda-rhel9, rhaiis/vllm-cuda-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-aws-cuda-rhel9, rhelai3/bootc-gcp-cuda-rhel9, rhelai3/bootc-azure-cuda-rhel9
    affected: workaround, no fix available
  • Red Hat AI Inference Server rhaii/vllm-cpu-rhel9, rhaii/vllm-tpu-rhel9, rhaii/vllm-rocm-rhel9, rhaiis/vllm-cpu-rhel9, rhaiis/vllm-tpu-rhel9, rhaii/vllm-gaudi-rhel9, +5 more Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/bootc-azure-rocm-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-llm-d-kv-cache-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-kserve-storage-initializer-rhel9
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
total
Assessed
4 mo ago

Exploit prediction

0.56% chance of exploitation in the next 30 days, higher than 47% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2 referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
OSV 3.1 8.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi vllm
<0.22.1
0.22.1

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-427 Uncontrolled Search Path Element

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.