MISFIRE

Browse / AI Framework and Platform Flaws / CVE-2025-6242

vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class

CVE-2025-6242 ยท 2025-10-07 high

Class
AI Framework and Platform Flaws (filed by a model that read the source)
Technique
Server-side request forgery
Affected
vllm (PyPI)
CVSS
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:L/A:H
EPSS
0.3% chance of exploitation in 30 days

How it works, in short

The media loader fetches any http, https or file URL supplied in a multimodal request without host restrictions, so the server can be made to reach internal addresses. (Our summary, written by a model. The source text is below.)

Details

Summary

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.

This vulnerability is particularly critical in containerized environments like llm-d, where a compromised vLLM pod could be used to scan the internal network, interact with other pods, and potentially cause denial of service or access sensitive data. For example, an attacker could make the vLLM pod send malicious requests to an internal llm-d management endpoint, leading to system instability by falsely reporting metrics like the KV cache state.

Vulnerability Details

The core of the vulnerability lies in the MediaConnector.load_from_url method and its asynchronous counterpart. These methods accept a URL string to fetch media content (images, audio, video).

https://github.com/vllm-project/vllm/blob/119f683949dfed10df769fe63b2676d7f1eb644e/vllm/multimodal/utils.py#L97-L113

The function directly processes URLs with http, https, and file schemes. An attacker can supply a URL pointing to an internal IP address or a localhost endpoint. The vLLM server will then initiate a connection to this internal resource.

Impact in llm-d Environments

The risk is significantly amplified in orchestrated environments such as llm-d, where multiple pods communicate over an internal network.

Delegating this security responsibility to an upper-level orchestrator like llm-d is problematic. The orchestrator cannot easily distinguish between legitimate requests initiated by the vLLM engine for its own purposes and malicious requests originating from user input, thus complicating traffic filtering rules and increasing management overhead.

Fix

See the --allowed-media-domains option discussed here: https://docs.vllm.ai/en/latest/usage/security.html#4-restrict-domains-access-for-media-urls

References

Source: GitHub Advisory Database, used under CC BY 4.0.