Arbitrary Code Injection Affecting vllm-cu130 package, versions <0.22.0-r0
Threat Intelligence
This vulnerability is trending on Twitter; this may indicate a growing threat.
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-MINIMOSLATEST-VLLMCU130-17370379
- published18 Jun 2026
- disclosed22 Jun 2026
Introduced: 18 Jun 2026
CVE-2026-41523 (opens in a new tab)How to fix?
Upgrade Minimos:latest vllm-cu130 to version 0.22.0-r0 or higher.
NVD Description
Note: Versions mentioned in the description apply only to the upstream vllm-cu130 package and not the vllm-cu130 package as distributed by Minimos.
See How to fix? for Minimos:latest relevant fixed versions and status.
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.
References
- https://www.cve.org/CVERecord?id=CVE-2026-41523
- https://github.com/advisories/GHSA-q8gq-377p-jq3r
- https://osv.dev/vulnerability/MINI-jx2c-gf52-2pw6
- https://osv.dev/vulnerability/CVE-2026-41523
- https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r
- https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c