FastChat Server-Side Request Forgery vulnerability

The SSRF vulnerability in fastchat allows an attacker to craft malicious requests through the /queue/join? endpoint. By manipulating the path parameter, an attacker can trick the server into making requests to unintended destinations. This could include accessing internal network services that are not directly exposed to the internet, or even querying the AWS metadata endpoint (if the application is deployed on AWS). Successful exploitation of this vulnerability could lead to the exposure of sensitive configuration data, API keys, or other credentials stored within the internal network. The blast radius extends to any internal systems accessible from the vulnerable fastchat instance, potentially enabling lateral movement and further compromise.

Organizations deploying fastchat for language model serving, particularly those running on AWS infrastructure, are at significant risk. Shared hosting environments where fastchat instances share network access with other tenants are also particularly vulnerable, as a successful SSRF attack could potentially compromise other services on the same host.

• python / server:

import requests
import urllib.parse

def check_ssrf(url):
    try:
        parsed_url = urllib.parse.urlparse(url)
        if parsed_url.scheme in ('http', 'https'):
            response = requests.get(url, timeout=5)
            print(f"URL: {url}, Status Code: {response.status_code}")
        else:
            print(f"Invalid URL scheme: {url}")
    except requests.exceptions.RequestException as e:
        print(f"Error accessing {url}: {e}")

# Example usage - check AWS metadata endpoint
check_ssrf('http://169.254.169.254/latest/meta-data/iam/security-credentials/')

• generic web:

curl -I 'http://your-fastchat-server/queue/join?path=http://169.254.169.254/latest/meta-data/iam/security-credentials/'

1. 2025-03-20Disclosure

   disclosure

1. Reserviert2024-11-21
2. Veröffentlicht2025-03-20
3. Geändert2025-03-21
4. EPSS aktualisiert2026-04-02

The primary mitigation for CVE-2024-11603 is to upgrade to a patched version of fastchat. Unfortunately, a specific fixed version is not provided in the CVE details. Until a patched version is available, consider implementing temporary workarounds such as restricting outbound network access from the fastchat server using a firewall or network segmentation. Implementing strict input validation on the /queue/join? endpoint to sanitize the path parameter is also crucial. Web Application Firewalls (WAFs) configured to block SSRF attempts can provide an additional layer of defense. Monitor logs for suspicious outbound requests originating from the fastchat server.