CVE-2026-54232
Last modified
CVE-2026-54232 is a high-severity vulnerability rated 8.8/10 on the CVSS scale. 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. EPSS estimates a 0.30% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | < 0.22.1 |
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2Exploit, Third Party Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-54232?
How severe is CVE-2026-54232?
How do I fix CVE-2026-54232?
Are you affected by CVE-2026-54232?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
