| Component | vLLM |
| Severity | high (CVSS 7.1) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:L |
| Published (NVD) | 2026-03-09 |
| Last modified | 2026-07-21 |
| Affected versions | vllm >= 0.15.1, < 0.17.0 |
| Fixed in | 0.17.0 |
| Weakness | CWE-918CWE-474 |
| CISA KEV | not listed |
NVD 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.
What to do
- Upgrade vLLM to
0.17.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-25960
- https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536
- https://github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f8221358002c0
- https://github.com/vllm-project/vllm/pull/34743
- https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc
- https://access.redhat.com/errata/RHSA-2026:24977
- https://access.redhat.com/errata/RHSA-2026:42644
- https://access.redhat.com/security/cve/CVE-2026-25960
- https://bugzilla.redhat.com/show_bug.cgi?id=2445892
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-25960.json
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...