High severity7.1NVD Advisory· Published Mar 9, 2026· Updated Jul 21, 2026
CVE-2026-25960
CVE-2026-25960
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | >= 0.15.1, < 0.17.0 | 0.17.0 |
Affected products
3Patches
Vulnerability mechanics
References
13- github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f8221358002c0nvdPatchWEB
- github.com/vllm-project/vllm/pull/34743nvdIssue TrackingPatchWEB
- github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536nvdExploitPatchVendor AdvisoryWEB
- github.com/advisories/GHSA-v359-jj2v-j536ghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-25960ghsaADVISORY
- access.redhat.com/errata/RHSA-2026:24977nvdWEB
- access.redhat.com/security/cve/CVE-2026-25960nvdWEB
- bugzilla.redhat.com/show_bug.cginvdWEB
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3411.yamlghsaWEB
- github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfcnvdNot ApplicableWEB
- pypi.org/project/vllmghsaWEB
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-25960.jsonnvdWEB
- access.redhat.com/errata/RHSA-2026:42644nvd
News mentions
0No linked articles in our index yet.