vllm-project · vLLM · published 2026-06-22
CVE-2026-41523vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution
Routine No exploitation evidence; EPSS 0.9%.
CVE-2026-41523 is not known to be exploited in the wild. EPSS estimates a 0.9% chance of exploitation in the next 30 days, higher than 60% of all CVEs. This vLLM vulnerability: CVSS 7.5 (v3.1), a successful attack gives total control of the component. Fixed upstream in vLLM 0.22.0. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.22.0.
Patch events
AI toolingvLLM
vLLM security release: 0.22.0
Upgrade to
0.22.0Why: Vendor security release for server software (most severe: CVE-2026-41523).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.9% (61th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 7.5 (v3.1)CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | total | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
< 0.22.0(affected)
Description (from the CVE record)#
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.
Quoted from the CVE Program record.