CVE-2026-54232
vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile
Description
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.
CVSS Vector Breakdown
AV:NAttack VectorAC:LAttack ComplexityPR:NPrivileges RequiredUI:RUser InteractionS:UScopeC:HConfidentialityI:HIntegrityA:HAvailabilityWeaknesses
Affected Products
Exploitability
Attack Graph
Click technique nodes to view MITRE ATT&CK details. Scroll to zoom, drag to pan.
MITRE ATT&CK
1 techniqueReferences
Timeline
Unlock Complete Vulnerability Intelligence
Get the full picture for CVE-2026-54232 and every CVE in our database. Create a free account — no credit card required.
Create Free Account