CVE-2026-54232
Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.56%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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 3.1
- 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- EPSS
- 0.56% probability · 45th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-427
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2Exploit, Third Party Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.