# CVE-2026-54232: vLLM dependency confusion in Dockerfile via flashinfer-jit-cache

Source: https://junglewise.ai/threats/cve-2026-54232-vllm-dependency-confusion-in-dockerfile-via-flashinfer-jit-cache  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-06-22. Updated: 2026-06-22  
License: CC BY 4.0 with a link back

CVE-2026-54232 · Severity: high · CVSS 8.8 · Published 2026-06-22

vLLM is a popular engine used to run and serve large language models (LLMs). A security flaw in its build process allows attackers to perform a 'dependency confusion' attack, where a malicious package is substituted for a legitimate one during the creation of the software's container image. If exploited, this allows an attacker to embed a backdoor in the software, potentially leading to the theft of sensitive user prompts, API keys, and proprietary model data from any organization using the affected versions.

Technologies: [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2026-54232 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-54232 being exploited in the wild.

**How severe is CVE-2026-54232?** High severity, with a CVSS score of 8.8, published 22 June 2026.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0,fixed=0.22.1.

**Is there a fix for CVE-2026-54232?** Yes. vllm (PyPI): upgrade to 0.22.1 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-54232 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-54232?** Check whether you run vllm (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- vllm (PyPI): upgrade to 0.22.1 or later

  ```sh
  pip install "vllm>=0.22.1"
  ```


## Technical details

A dependency confusion vulnerability exists in the vLLM Dockerfile due to the use of the `flashinfer-jit-cache` package. The build process uses `uv pip install` with `--extra-index-url` pointing to a custom repository, but the package name was not reserved on the public PyPI registry. Combined with the global setting `UV_INDEX_STRATEGY="unsafe-best-match"`, the installer may prioritize a malicious package uploaded to PyPI over the intended custom version. An attacker who registers the package on PyPI can achieve root-level remote code execution during the Docker build process. This allows for the insertion of a persistent backdoor into the final container image, enabling the exfiltration of prompts, credentials, and model weights. The issue is resolved in version 0.22.1.

## Affected products

- vllm-project vLLM < 0.22.1

## Identifiers

- CVE-2026-54232
- PYSEC-2026-227

## Timeline

- 2026-06-09: advisory: GitHub Security Advisory published
- 2026-06-22: disclosed: CVE published to NVD
- 2026-06-22: patched: Fix confirmed in version 0.22.1

## References

- [https://github.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2](https://github.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2)

## Related threats

- [vLLM chat template resource exhaustion DoS](https://junglewise.ai/threats/cve-2026-115918-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server](https://junglewise.ai/threats/cve-2026-115917-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM off-by-one error in tokenizer max_token_id validation](https://junglewise.ai/threats/cve-2026-115916-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM image format validation bypass in media processing](https://junglewise.ai/threats/cve-2026-115915-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM denial of service in DeepSeek-OCR image processing](https://junglewise.ai/threats/cve-2026-115914-vllm-is-an-inference-and-serving-engine-for-large-language)