CVE-2026-25960: vLLM SSRF Protection Bypass Vulnerability

vllm Updated 09 Mar 2026

Summary

09/03/2026
Yes i
Moderate
5.4

CVE-2026-25960: vLLM has SSRF Protection Bypass. Affects vllm versions >= 0.15.1, < 0.17.0. Fixed in 0.17.0. How to fix ↓

Free scan

Check if this vulnerability affects your application

Upload a manifest or SBOM and we'll show whether you're affected, plus every other risky package in the same scan.

Check my app free

No signup required · Results in about 60 seconds

Upload your dependency manifest or SBOM

Drag & drop your file here or

Java Javascript PHP Python Go Rust Ruby Dart C/C++ Elixir CycloneDX SPDX

Upload a supported dependency manifest or SBOM. No installation or source-code access required.

See supported files and SBOM formats
SBOM sbom.json · bom.json · bom.xml · *.spdx.json · *.cdx.json · *.cdx.xml
Java pom.xml · gradle.lockfile · buildscript-gradle.lockfile
Javascript package-lock.json · yarn.lock · pnpm-lock.yaml
PHP composer.lock
Python poetry.lock · requirements.txt · Pipfile.lock
Go go.mod
Rust Cargo.lock
Ruby Gemfile.lock
Dart pubspec.lock
C/C++ conan.lock
Elixir mix.lock
Enter your work email to receive your report link.

Verify your email to view the full report and start 30 days of continuous monitoring. No credit card required.

Sponsored Devnack Your last release was probably never penetration tested Manual testing by engineers who build software, not an auditor's checklist. Trusted by teams at Swift and Google Talk to Devnack

Background

vLLM is an open-source library designed for efficient and scalable machine learning model serving. It allows users to load models from various sources, including URLs. However, due to a flaw in its URL parsing mechanism, the library is susceptible to Server-Side Request Forgery (SSRF) attacks, which can lead to unauthorized access to internal or external services.

Vulnerability Detail

The vulnerability arises from a bypass in the SSRF protection implemented in the load_from_url_async method of vLLM. The inconsistency between the URL parsing behavior of urllib3 and aiohttp allows attackers to manipulate URLs to access unauthorized resources. Specifically, the validation layer uses urllib3 to parse URLs, which treats backslashes differently than aiohttp, leading to potential SSRF attacks. An attacker can provide a malicious URL that passes validation but ultimately redirects requests to an unintended host, compromising the security of the application.

How To Fix

Latest published version: 0.32.0 as of 22 Oct 2026

pip install --upgrade "vllm==0.32.0"

Upgrading to it may include breaking changes; the version below is the minimum fixed release for this vulnerability.

If you need the minimum change

0.17.0

This is the first release that contains the fix.

pip install --upgrade "vllm==0.17.0"

Tip — Not sure which version your app runs? Vulert can match this fix to it. Scan free →

Workaround

As a temporary workaround, avoid using URLs that contain backslashes or ensure that your application has additional validation checks in place to prevent SSRF attacks. For example, you can implement a custom URL validation function that strictly checks for allowed hosts.

Conclusion

The CVE-2026-25960 vulnerability in vLLM represents a significant risk due to its SSRF protection bypass. Users are strongly advised to update to the latest version to mitigate potential attacks. Additionally, implementing strict URL validation can help reduce the risk until the update is applied.

See every vulnerability recorded for vllm →

Share this vulnerability

FAQ

Server-Side Request Forgery (SSRF) is a vulnerability that allows an attacker to send crafted requests from the server to internal or external resources, potentially leading to data exposure or unauthorized access.

You can check if your application is affected by using the Vulert playground at Vulert Scanner. This tool allows you to monitor and alert for open-source vulnerabilities in your software without requiring any installation.

If exploited, this vulnerability can allow attackers to access sensitive internal services, leading to data leaks, unauthorized actions, or further exploitation of the system.

While updating to the patched version is the best solution, you can implement additional validation checks on URLs to prevent SSRF attacks as a temporary measure.

The CVSS score of this vulnerability is 5.4, indicating a moderate level of severity.

Related vulnerabilities

Recent vulnerabilities recorded for vllm.

How To Fix

Latest published version: 0.32.0 as of 22 Oct 2026

pip install --upgrade "vllm==0.32.0"

Upgrading to it may include breaking changes; the version below is the minimum fixed release for this vulnerability.

If you need the minimum change

0.17.0

This is the first release that contains the fix.

pip install --upgrade "vllm==0.17.0"

Tip — Not sure which version your app runs? Vulert can match this fix to it. Scan free →

Subscribe to Vulert on Telegram
Daily digest of new CVEs, critical and high severity, affected packages and fixes — plus a weekly roundup.
Join the channel →
Help improve this record
Report an issue or send feedback