Medium [CVE-2026-54232] Arbitrary code execution via dependency confusion during Docker build
This medium-severity Red Hat Linux advisory covers CVE-2026-54232 affecting Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3.
Aggregated and source-linked by VulniPulse. Data sources, validation and limitations.
VulniPulse record published Record updated
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.
CVE-2026-54232 is a build-time dependency confusion issue in upstream vLLM Dockerfiles before 0.22.1. It does not allow remote exploitation of a running vLLM inference service.
Red Hat OpenShift AI is not affected. Red Hat AI Inference Server and RHEL AI CUDA images that include flashinfer-jit-cache are in scope for build-process review, but Red Hat has no evidence that shipped images were compromised.
Red Hat severity: Moderate — CVSS 5.7 (CVSS:3.1/AV:N/AC:H/PR:H/UI:R/S:U/C:H/I:H/A:N). Weakness: CWE-426.
Affected Red Hat products: Red Hat AI Inference Server; Red Hat Enterprise Linux AI (RHEL AI) 3.
Is CVE-2026-54232 exploited?
No exploitation is reported in the sources VulniPulse tracks: CVE-2026-54232 is not in the CISA KEV catalog (checked ) and this advisory does not report exploitation. That is not proof the vulnerability cannot be exploited.
How do I fix CVE-2026-54232?
Upgrade to a fixed release named by Red Hat:
- 0.6.11
- 0.22.1
Confirm against the vendor advisory before you patch.
- < 0.22.1
Official advisory · high-confidence parse· fetched 14 days ago·verify at source
- 0.6.11
- 0.22.1
Official advisory · high-confidence parse· fetched 14 days ago·verify at source
Mitigation checklist
- Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
Official advisory · high-confidence parse· fetched 14 days ago·verify at source
Get an email when Red Hat publishes the next one.
See Red Hat's last 90 days of advisories first. Then choose one product with live alerts free for life, or a free month of real-time alerts on everything with the severity, the fixed version and the vendor's link (card needed, then US$15/month; we email you before the first charge).
More Red Hat Linux advisories
- CVE-2026-48710May 26, 2026Security restriction bypass via malformed HTTP Host header
- CVE-2026-119977Oct 31, 2026Arbitrary code execution via predictable upgrade staging paths
- CVE-2026-111497Oct 22, 2026Out-of-Bounds Write in Google Brotli Decoder
- CVE-2026-109619Oct 21, 2026fatal error handling retains stale request state leading to use-after-free
- CVE-2026-109618Oct 21, 2026OOM bailout during request parsing leads to memory corruption and RCE
- CVE-2026-97229Oct 13, 2026integer overflow issue in CI/CD regular expression compiler
iPhone and Android apps · New on the App Store
Monitor future Red Hat Linux CVEs from your phone.
Choose a whole vendor or a precise platform, then receive matching security advisories by phone notification, email, or both. Coverage follows 34 official vendor sources and 160+ reviewed platform categories.
Discussion(0)
No comments yet. Share field notes, upgrade gotchas, or questions — verify against the vendor advisory before acting on community advice.
Sign in to join the discussion.