oM noM Security Feeds cve
vulnerability context

CVE-2026-54232

CVSS 8.8 HIGHEPSS 22%CWE-427OTX 8 pulses

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 exfilt...

Published 2026-06-22 · last modified 2026-06-24

details

CISA KEV status
Not in catalog
CVSS v3
8.8 / HIGH
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS
22% percentile (score 0.0030)
CWE
CWE-427
OTX pulses
8 total, 0 recent

source mentions 2

source consensus

  • Bluesky:@cyberhub.blog
  • Bluesky
Want the 3-bullet summary of CVE-2026-54232, plus webhook alerts when KEV is updated? Pro is $10/mo.