CVE-2026-41523
HIGH EPSS 34.3%
Published Jun 22, 20261w ago · Modified Jun 23, 20261w ago
7.5 CVSS 3.1
Published Jun 22, 2026 1w ago
Last Modified Jun 23, 2026 1w 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.
CVSS Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H Attack Vector Network
Attack Complexity High
Privileges Required None
User Interaction Required
Scope Unchanged
Confidentiality High
Integrity High
Availability High
Threat Intelligence
EPSS Exploit Probability
34.3% percentile
Exploit & Patch Status
No Known Exploit
No Patch Available
Weaknesses 2
CWE-617
CWE-94 Improper Control of Generation of Code (Code Injection) Injection
References 3
- github.com https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r
- huntr.com https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c
Remediation
No remediation data recorded yet
Check vendor advisories and the NVD entry for patch availability.