CVE-2026-54232
HIGHDescription
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.
How to fix
TridentStack Control can deploy fixes like this automatically across your Windows, macOS, and Linux fleet. See how it works
Remediation is compiled from vendor and distribution security advisories. Always confirm against the linked source for your exact version and platform.
CVSS v3 Vector
Exploitability
Impact
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Exploit Intelligence
Moderate risk: more likely to be exploited than 44% of all known CVEs.
References
Related Vulnerabilities
Other CWE-427 vulnerabilities, ordered by exploit likelihood. View all
| CVE | Severity | CVSS | EPSS | Exploited | Fix |
|---|---|---|---|---|---|
| CVE-2020-27955 | Critical | 9.8 | 83% | - | - |
| CVE-2017-6517 | Critical | 9.8 | 46% | - | - |
| CVE-2020-3153 | Medium | 6.5 | 28% | KEV + Ransom | Fix |
| CVE-2024-48990 | High | 7.8 | 20% | - | Fix |
| CVE-2019-9491 | High | 7.8 | 13% | - | - |
| CVE-2022-2334 | High | 7.2 | 12% | - | - |
Common questions
How do I fix CVE-2026-54232?
Upgrade vllm to 0.22.1 or later.
Is CVE-2026-54232 being actively exploited?
Not that we know of. CVE-2026-54232 is not in the CISA Known Exploited Vulnerabilities catalog. Its EPSS score of 0.56% is the estimated probability that it will be exploited in the next 30 days. That is higher than 44% of all scored CVEs.
How severe is CVE-2026-54232?
CVE-2026-54232 has a CVSS v3 base score of 8.8, rated high. CVSS rates the technical impact if the vulnerability is exploited, not how likely that is, so weigh it alongside the exploit-prediction score when you decide what to patch first.
What does CVE-2026-54232 affect?
Published advisories record a fix for vllm (NVD). Only products with a sourced advisory are listed, so treat this as what we can cite rather than a complete inventory.
Embed a live status badge for CVE-2026-54232
Markdown
[](https://tridentstack.com/cve/CVE-2026-54232)HTML
<a href="https://tridentstack.com/cve/CVE-2026-54232"><img src="https://tridentstack.com/cve/badge/CVE-2026-54232.svg" alt="CVE-2026-54232"></a>Find and fix vulnerabilities across your fleet
TridentStack Control continuously scans your Windows, macOS, and Linux fleet for known vulnerabilities, prioritizes them by severity and active exploitation, and patches them automatically.
This product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2026-06-24.