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.
{
"cwe_ids": [
"CWE-617",
"CWE-94"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/41xxx/CVE-2026-41523.json",
"cna_assigner": "GitHub_M"
}{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"source": [
"CPE_RANGE",
"REFERENCES"
],
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "0.22.0"
}
]
}