vllm-project · vLLM · published 2026-06-22
CVE-2026-54232vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile
Routine No exploitation evidence; EPSS 0.6%.
CVE-2026-54232 is not known to be exploited in the wild. EPSS estimates a 0.6% chance of exploitation in the next 30 days, higher than 47% of all CVEs. This vLLM vulnerability: CVSS 8.8 (v3.1), a successful attack gives total control of the component. Fixed upstream in vLLM 0.22.1. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.22.1.
Patch events
AI toolingvLLM
vLLM security release: 0.22.1
Upgrade to
0.22.1Why: Vendor security release for server software (most severe: CVE-2026-54232).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.6% (48th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 8.8 (v3.1)CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | total | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
< 0.22.1(affected)
Description (from the CVE record)#
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.
Quoted from the CVE Program record.