CVE-2026-25960
HIGHCVSS v3
7.1
HIGH
EPSS Score
0.0%
exploit probability
CISA KEV
No
known exploited
Exploitation
—
SSVC status
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
Technical Details
- CVSS v3 Vector
- 3.1
- Published
- 3/9/2026
- Last Modified
- 3/18/2026
Frequently Asked Questions
What is CVE-2026-25960?
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
Is CVE-2026-25960 actively exploited?
Active exploitation of CVE-2026-25960 has not been confirmed. The EPSS score is 0.0%, indicating the estimated probability of exploitation in the next 30 days.
What is the CVSS score for CVE-2026-25960?
CVE-2026-25960 has a CVSS v3 base score of 7.1 (HIGH severity), with vector string 3.1.
Is CVE-2026-25960 affecting your environment?
Use isMalicious to check if any of your IPs or domains are associated with this vulnerability's IOCs.