CVE-2025-66448Network attack vector

Host code execution via unchecked auto_map resolution

Published Dec 1, 2025 · Updated Dec 2, 2025

Code injection in vLLM before 0.11.1 allows remote authenticated users to execute arbitrary commands by inducing a crafted model load. Nemotron_Nano_VL_Config resolves an auto_map value with get_class_from_dynamic_module and immediately instantiates the fetched class. Loading an attacker-selected frontend repository therefore executes Python from a separate backend repository even when trust_remote_code is false.

CVSS severity7.1
High
EPSS probability0.66%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Code injection in vLLM before 0.11.1 allows remote authenticated users to execute arbitrary commands by inducing a crafted model load. Nemotron_Nano_VL_Config resolves an auto_map value with get_class_from_dynamic_module and immediately instantiates the fetched class. Loading an attacker-selected frontend repository therefore executes Python from a separate backend repository even when trust_remote_code is false.

The record

CVE
CVE-2025-66448
Published
Dec 1, 2025
Updated
Dec 2, 2025
Vendor
vLLM Project
Product
vLLM
Classifications
CWE-94, T1059.006
Attack vector
network
Privileges
authenticated

Timeline

How it unfolded

  1. Dec 1, 2025CVE publishedPublication date reported by the CVE source.
  2. Dec 2, 2025Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=< 0.11.1

What conditions does exploitation require?

Attack vectornetwork
Required privilegesauthenticated

What is affected?

vLLM Project · vLLMversion=< 0.11.1

Published CVSS scores

7.1GitHubCVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-94Improper Control of Generation of Code ('Code Injection')
T1059.006Python

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo