CVE-2026-22807
Description
A flaw was found in vLLM, an inference and serving engine for large language models (LLMs). This vulnerability allows a remote attacker to achieve arbitrary code execution on the vLLM host during model loading. This occurs because vLLM loads Hugging Face auto_map dynamic modules without properly validating the trust_remote_code setting. By influencing the model repository or path, an attacker can execute malicious Python code at server startup, even before any API requests are handled.
Statement
This vulnerability is rated Important for Red Hat as vLLM, an inference and serving engine for large language models, is vulnerable to arbitrary code execution. An attacker influencing the model repository or path can execute malicious Python code during server startup, affecting vLLM versions 0.10.1 through 0.13.x.
Mitigation
To mitigate this issue, ensure that vLLM instances are configured to load models only from trusted and verified repositories. Restrict access to the model repository path to prevent unauthorized modification or introduction of malicious code. Implement strict access controls and integrity checks for all model sources.
Common Vulnerability Scoring System (CVSS) Score Details
Info alert:Important note
CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).
CVSS v3 Score Breakdown
| Red Hat | NVD | cve.org | |
|---|---|---|---|
| Base Score | 8.8 | 9.8 | 8.8 |
| Attack Vector | Network | Network | Network |
| Attack Complexity | Low | Low | Low |
| Privileges Required | None | None | None |
| User Interaction | Required | None | Required |
| Scope | Unchanged | Unchanged | Unchanged |
| Confidentiality | High | High | High |
| Integrity Impact | High | High | High |
| Availability Impact | High | High | High |
Vector
Red Hat: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
NVD: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
cve.org: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Understanding the Weakness (CWE)
Access Control
Technical Impact: Bypass Protection Mechanism
In some cases, injectable code controls authentication; this may lead to a remote vulnerability.
Access Control
Technical Impact: Gain Privileges or Assume Identity
Injected code can access resources that the attacker is directly prevented from accessing.
Integrity,Confidentiality,Availability
Technical Impact: Execute Unauthorized Code or Commands
When a product allows a user's input to contain code syntax, it might be possible for an attacker to craft the code in such a way that it will alter the intended control flow of the product. As a result, code injection can often result in the execution of arbitrary code. Code injection attacks can also lead to loss of data integrity in nearly all cases, since the control-plane data injected is always incidental to data recall or writing.
Non-Repudiation
Technical Impact: Hide Activities
Often the actions performed by injected control code are unlogged.
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.
