LLMMedium
CVE-2026-25960: vLLM is an inference and serving engine for large language models (LLMs). The SSRF protection fix fo…
- Occurred
- Mar 9, 2026
- Published
- Mar 9, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-25960
- cvss:HIGH
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: CVE describes SSRF vulnerability in vLLM LLM serving engine, representing a notable technical failure without reported mass harm.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8