- CVSS
- HIGH · 7.5v3.1CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
- Published
- 2026-06-22
- Weakness
- CWE-94, CWE-617, CWE-617
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-41523
Description
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://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
- https://access.redhat.com/security/cve/CVE-2026-41523
- https://bugzilla.redhat.com/show_bug.cgi?id=2491582
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-41523.json
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-41523 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.