CVE-2026-41523 - vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution
CVE ID :CVE-2026-41523
Published : June 22, 2026, 10:18 p.m. | 3 hours, 22 minutes ago
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.
Severity: 0.0 | NA
Visit the link for more details, such as CVSS details, affected products, timeline, and more...
Published : June 22, 2026, 10:18 p.m. | 3 hours, 22 minutes ago
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.
Severity: 0.0 | NA
Visit the link for more details, such as CVSS details, affected products, timeline, and more...