vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution

Summary

CVE	CVE-2026-41523
State	PUBLISHED
Assigner	GitHub_M
Source Priority	CVE Program / NVD first with legacy fallback
Published	2026-06-22 23:16:30 UTC
Updated	2026-07-07 12:16:42 UTC
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.

Risk And Classification

Primary CVSS: v3.1 7.5 HIGH from ADP

CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H

EPSS: 0.004840000 probability, percentile 0.382530000 (date 2026-07-08)

Problem Types: CWE-94 | CWE-617 | CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection') | CWE-617 CWE-617: Reachable Assertion | CWE-617 Reachable Assertion

Version	Source	Type	Score	Severity	Vector
3.1	ADP	CVSS	7.5	HIGH	`CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H`
3.1	[email protected]	Secondary	7.5	HIGH	`CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H`
3.1	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	Secondary	7.5	HIGH	`CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H`
3.1	CNA	DECLARED	7.5	HIGH	`CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H`

CVSS v3.1 Breakdown

Attack Vector

Network

Attack Complexity

High

Privileges Required

None

User Interaction

Required

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H

NVD Known Affected Configurations (CPE 2.3)

Type	Vendor	Product	Version	Update	Edition	Language
Application	Vllm	Vllm	All	All	All	All

Vendor Declared Affected Products

Source	Vendor	Product	Version	Platforms
CNA	Vllm-project	Vllm	affected < 0.22.0	Not specified
ADP	Red Hat	Red Hat AI Inference Server 3.2	Not specified	Not specified
ADP	Red Hat	Red Hat AI Inference Server	Not specified	Not specified
ADP	Red Hat	Red Hat Enterprise Linux AI RHEL AI 3	Not specified	Not specified
ADP	Red Hat	Red Hat OpenShift AI RHOAI	Not specified	Not specified

References

Reference	Source	Link	Tags
github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r	[email protected]	github.com	Exploit, Third Party Advisory
huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c	[email protected]	huntr.com	Third Party Advisory
security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-41523.json	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	security.access.redhat.com
access.redhat.com/errata/RHSA-2026:36006	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	access.redhat.com
bugzilla.redhat.com/show_bug.cgi	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	bugzilla.redhat.com
github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c0...	[email protected]	github.com	Patch
access.redhat.com/errata/RHSA-2026:36005	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	access.redhat.com
access.redhat.com/security/cve/CVE-2026-41523	0b0ca135-0b70-47e7-9f44-1890c2a1c46c	access.redhat.com
CVE Program record	CVE.ORG	www.cve.org	canonical
NVD vulnerability detail	NVD	nvd.nist.gov	canonical, analysis

No vendor comments have been submitted for this CVE.

Additional Advisory Data

Source	Time	Event
ADP	2026-06-22T23:01:00.799Z	Reported to Red Hat.
ADP	2026-06-22T22:18:14.494Z	Made public.

Solutions

ADP: RHSA-2026:36005: Red Hat AI Inference Server 3.2

ADP: RHSA-2026:36006: Red Hat AI Inference Server 3.2

Workarounds

ADP: Avoid running vLLM with python -O or PYTHONOPTIMIZE=1 until updated packages are available. Only load models from trusted sources. Restrict who can deploy or update models on inference endpoints. Apply network access controls and authentication in front of vLLM APIs.

There are currently no legacy QID mappings associated with this CVE.