CVE-2026-25960

Published: Mar 09, 2026 Last Modified: Mar 11, 2026
ExploitDB:
Other exploit source:
Google Dorks:
HIGH 7,1
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: none
Scope: unchanged
Confidentiality: high
Integrity: none
Availability: low

Description

AI Translation Available

vLLM is an inference and serving engine for large language models (LLMs). The SSRF protection fix for CVE-2026-24779 add in 0.15.1 can be bypassed in the load_from_url_async method due to inconsistent URL parsing behavior between the validation layer and the actual HTTP client. The SSRF fix uses urllib3.util.parse_url() to validate and extract the hostname from user-provided URLs. However, load_from_url_async uses aiohttp for making the actual HTTP requests, and aiohttp internally uses the yarl library for URL parsing. This vulnerability in 0.17.0.

EPSS (Exploit Prediction Scoring System)

Trend Analysis

EPSS (Exploit Prediction Scoring System)

Prevede la probabilità di sfruttamento basata su intelligence sulle minacce e sulle caratteristiche della vulnerabilità.

EPSS Score
0,0002
Percentile
0,0th
Updated

EPSS Score Trend (Last 7 Days)

918

Server-Side Request Forgery (SSRF)

Incomplete
Common Consequences
Security Scopes Affected:
Confidentiality Integrity Access Control
Potential Impacts:
Read Application Data Execute Unauthorized Code Or Commands Bypass Protection Mechanism
Applicable Platforms
Technologies: AI/ML, Web Based, Web Server
View CWE Details
https://github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f8221358…
https://github.com/vllm-project/vllm/pull/34743
https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc
https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536