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.
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| vllm-project | vllm | affected |
|
No data.
No data.
No data.
Project Subscriptions
No data.
Advisories
| Source | ID | Title |
|---|---|---|
 Github GHSA |
GHSA-q8gq-377p-jq3r | vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution |
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Mon, 22 Jun 2026 22:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution | |
| Weaknesses | CWE-617 CWE-94 |
|
| References |
| |
| Metrics |
cvssV3_1
|
Projects
Sign in to view the affected projects.
MITRE
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-06-22T22:18:14.494Z
Reserved: 2026-04-20T18:18:50.682Z
Link: CVE-2026-41523
Vulnrichment
No data.
NVD
No data.
Redhat
No data.
OpenCVE Enrichment
No data.