SSRF in Red Hat Ai Inference Server
CVE-2025-6242
A Server-Side Request Forgery (SSRF) vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The load_from_url and load_from_url_async methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows an attacker to coerce the vLLM server into making arbitrary requests to internal network resources.
Vulnerability class: SSRF (Server-Side Request Forgery)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.1 (High). Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:H.
EPSS exploit prediction
EPSS 0.003, 17.0th percentile (last changed ); unchanged over 30 days. About EPSS.
Affected products
Weakness classification (CWE)
Public exploits and proof-of-concept code
Also mentioned in 1 other repository (fkie-cad/nvd-json-data-feeds). These reference the CVE in a list, notes or a scanner and are not exploit code for it.
References
- access.redhat.com/security/cve/CVE-2025-6242 (vdb-entry)
- RHBZ#2373716 (issue-tracking)