CVE-2025-6242 Vllm: server side request forgery (ssrf) in mediaconnector
Attackers can force the vLLM server to make arbitrary requests to internal network resources via user-provided URLs in the MediaConnector class.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2025-6242?
CVE-2025-6242 is a high-severity server-side request forgery vulnerability in Red Hat AI Inference Server, published on 7 Oct 2025. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
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.
Weakness: CWE-918
Which versions are affected by CVE-2025-6242?
3 open source packages ship an affected version, including vllm.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | From 0.5.0 | 0.11.0 |
vllm PyPI | From 0.5.0 | 0.11.0 |
vllm PyPI | From 0.5.0 | 0.11.0 |
How do I fix CVE-2025-6242?
Upgrade vllm to 0.11.0 or later.
Upgrade, and send outbound requests through an allow-list that blocks internal addresses. More about Server-side request forgery.
Is CVE-2025-6242 being exploited?
There is no known exploitation of CVE-2025-6242 in the wild and no public exploit code.
Sources
Also known as GHSA-3f6c-7fw2-ppm4, PYSEC-2026-2011.