CVE-2026-41523
CWE-94Published: June 22, 2026· Updated: Jun 24, 2026
Official 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.
Technical Analysis
CVE-2026-41523 can be exploited remotely over the network without requiring physical or adjacent access, significantly expanding the attack surface for threat actors.
Exploitation does not require any privileges, though user interaction (Required) is needed, which slightly reduces the risk of mass automated attacks.
A successful exploit results in complete confidentiality breach (data exposure), full integrity compromise (data manipulation), availability disruption (denial of service), with a CVSS base score of 7.5.
CVSS v3.1 Vector Breakdown
Affected Vendors & Products
Exploit & PoC Resources
Official Patches & Advisories
All References (3)
Quick Facts
Related CVEs (CWE-94)
Recommended Actions
- →Apply vendor patches immediately
- →Monitor CVE-2026-41523 in threat intel feeds
- →Review IDS/IPS signatures for exploitation attempts