Monitor vulnerabilities like this one.
Sign up free to get alerted when software you use is affected.
7.1
vLLM Large Language Model Engine Can Access Unauthorized URLs
GHSA-v359-jj2v-j536
CVE-2026-25960
GHSA-v359-jj2v-j536
Summary
A security fix for vLLM was recently updated, but it can still be circumvented. This means an attacker could potentially trick the system into accessing unauthorized websites. To stay secure, update to the latest version of vLLM.
What to do
- Update vllm to version 0.17.0.
Affected software
| Vendor | Product | Affected versions | Fix available |
|---|---|---|---|
| – | vllm | > 0.15.1 , <= 0.17.0 | 0.17.0 |
Original title
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 inconsist...
Original 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.
ghsa CVSS3.1
5.4
Vulnerability type
CWE-918
Server-Side Request Forgery (SSRF)
- https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc
- https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536
- https://github.com/vllm-project/vllm/pull/34743
- https://github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f82213580...
- https://github.com/advisories/GHSA-v359-jj2v-j536
- https://github.com/vllm-project/vllm Product
- https://nvd.nist.gov/vuln/detail/CVE-2026-25960
Published: 9 Mar 2026 · Updated: 13 Mar 2026 · First seen: 9 Mar 2026