Review reviewHigh

CVE-2026-41523

vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat AI Inference Server

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
7.5
EPSS
0.75%
51.3% percentile
CISA KEV
Not listed
Published
2026.06.23
PRIORITY ASSESSMENT

Review review

The CVSS severity warrants an early asset and exposure review.

Known exploitationNot established by KEV
Exploit probability0.75%
Technical severityCVSS 7.5

Vulnerability overview

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.

Affected product and versions

Product
vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat AI Inference Server
Affected versions
>= < 0.22.0, < 0.22.0
Fixed versions
0.22.0

Recommended response sequence

Confirm exposure before applying a vendor-supported change.

Full remediation guide
  1. 1
    Identify

    Confirm that vllm-project vllm, Red Hat AI Inference Server 3.2, Red Hat AI Inference Server and an affected version are present.

  2. 2
    Prioritize

    Combine exploitation signals with asset exposure and business criticality.

  3. 3
    Remediate

    Follow the vendor advisory or supported update path and preserve rollback options.

  4. 4
    Verify

    Recheck the version, service health, access paths, and relevant logs.

Technical data

CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
CWE
CWE-617, CWE-94