CVE-2026-41523
HIGH
7.5
CVSS 3.1
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.
Metadata
Severity & Metrics
7.5
HIGH CVSS 3.1
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Affected products (1)
| Vendor | Product | Platform | Versions |
|---|---|---|---|
| vllm-project | vllm | — | < 0.22.0 |
Weakness (CWE)
CVSS scores (1)
| Score | Severity | Version | Source | Vector |
|---|---|---|---|---|
| 7.5 | HIGH | 3.1 | cna | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H |
References (3)
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r
- https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3 https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3
- https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c