CVE-2026-25960
🟡 Monitoruj
Obejście ochrony SSRF w vLLM umożliwia atakującym dostęp do wewnętrznych zasobów sieciowych poprzez nieprawidłowe parsowanie URL.
CVSS
7.1
EPSS
0.0%
Exploit
poc
Vendor
vllm
Opis źródłowy (NVD)
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.
exploit ssrf
Brak patcha
Źródła i daty
| Źródło | Wartość |
|---|---|
| NVD – CVSS | 7.1 |
| CISA KEV (aktywnie wykorzystywane) | Nie |
| FIRST EPSS (prawdopodobieństwo exploita) | 0.0% |
| Opublikowano (NVD) | 2026-03-09 21:16:15 UTC |
| Ostatnia modyfikacja (NVD) | 2026-03-18 18:36:10 UTC |
Referencje
- https://github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f8221358002c0 (security-advisories@github.com) [Patch]
- https://github.com/vllm-project/vllm/pull/34743 (security-advisories@github.com) [Issue Tracking, Patch]
- https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc (security-advisories@github.com) [Not Applicable]
- https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536 (security-advisories@github.com) [Exploit, Patch, Vendor Advisory]