CVE-2026-25960
Last modified
CVE-2026-25960 is a critical-severity vulnerability rated 9.8/10 on the CVSS scale. 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. EPSS estimates a 0.44% chance of exploitation in the next 30 days.
Description
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.15.1, < 0.17.0 |
References
- https://github.com/vllm-project/vllm/pull/34743Issue Tracking, Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536Exploit, Patch, Vendor Advisory
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2026-25960?
How severe is CVE-2026-25960?
How do I fix CVE-2026-25960?
Are you affected by CVE-2026-25960?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST