Servers and applications
CVE-2026-54232
Dependency Confusion Vulnerability in vLLM Dockerfile
- Severity
- High 8.8
- Published
- 9 Jun 2026
- Last changed
- 25 Oct 2026
- Added to UpHeron
- 3 Nov 2026
- Fixed in
- 0.22.1
- Exploit chance
- 0.6% in the next 30 daysHigher than 47% of CVEs. EPSS by FIRST, 19 Nov 2026
- Weakness
- CWE-427
- Attack
- Over the network · No login needed · Needs someone to click or open something
- Attacker can
- Read data · Change data · Take it down
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H- Also known as
- GHSA-jrf6-vqxq-pjv2
- Sources
- NVD, Project advisories (GitHub)
Description
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.
After looking into this issue, I noticed that another individual already claimed the flashinfer-jit-cache package on PyPi and published a "sec-test" PoC to https://pypi.org/project/flashinfer-jit-cache/ on March 5th. The package does not appear overtly malicious and has been quarantined by PyPi.
Affected software
| Software | Affected versions |
|---|---|
vLLMServers and applications · cpe:a:vllm:vllm |
|
vLLMServers and applications · github:vllm-project/vllm |
|
About vLLM
open-source software for large language model inference
- Docker Hub pulls
- 44,195,225Docker Hub, 15 Nov 2026
- GitHub stars
- 96,943GitHub, 15 Nov 2026
- Forks
- 24,836GitHub, 15 Nov 2026
- Latest release
- v0.33.0rc3GitHub, 15 Nov 2026
- Released
- 2 Nov 2026GitHub
- License
- Apache Software License 2.0Wikidata
- First published on GitHub
- 9 Feb 2023GitHub
Website Source code Docker image
Vulnerabilities in vLLM
- In our list
- 169
- Published in the last 12 months
- 150
- Critical, last 12 months
- 6
- High, last 12 months
- 63
- Known exploited
- 0
- CVE-2026-130686vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image RequestsHigh 8.7 18 Nov 2026
- CVE-2026-130684vLLM before 0.33.0 Path Traversal via speculators_config verifier.name_or_pathMedium 5.3 18 Nov 2026
- CVE-2026-130685vLLM 0.28.0 before 0.33.0 Unauthenticated DoS via Out-of-Range Prompt Token IDHigh 8.7 18 Nov 2026
- GHSA-xgh8-qwjh-q853/v1/systemone bypasses the --trust-request-chat-template gateMedium 6.5 18 Nov 2026
- CVE-2026-129356vllm-project vllm Common Prefix single_type_kv_cache_manager.py race conditionLow 2.3 15 Nov 2026
- CVE-2026-126394vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_framesMedium 6.9 13 Nov 2026
References
- NVD https://nvd.nist.gov/vuln/detail/CVE-2026-54232
- CVE.org https://www.cve.org/CVERecord?id=CVE-2026-54232
- GitHub Advisory Database https://github.com/advisories/GHSA-jrf6-vqxq-pjv2
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2