CVE-2025-53109
Model Context Protocol Servers Vulnerable to Path Validation Bypass via Prefix Matching and Symlink Handling
Description
Model Context Protocol Servers is a collection of reference implementations for the model context protocol (MCP). Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files via symlinks within allowed directories. Users are advised to upgrade to 0.6.4 or 2025.7.01 resolve.
INFO
Published Date :
July 2, 2025, 3:15 p.m.
Last Modified :
July 3, 2025, 3:13 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
Affected Products
The following products are affected by CVE-2025-53109
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
No affected product recoded yet
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 4.0 | HIGH | [email protected] |
Solution
- Upgrade Filesystem to version 0.6.4 or 2025.7.01.
Public PoC/Exploit Available at Github
CVE-2025-53109 has a 10 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2025-53109.
| URL | Resource |
|---|---|
| https://github.com/modelcontextprotocol/servers/commit/d00c60df9d74dba8a3bb13113f8904407cda594f | |
| https://github.com/modelcontextprotocol/servers/security/advisories/GHSA-q66q-fx2p-7w4m |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2025-53109 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2025-53109
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Guía definitiva de Claude Code - Traducción al español latinoamericano
TypeScript JavaScript Shell Python
Zero-dependency MCP security linter — 54 OWASP-mapped checks, 56 malicious packages, 28 CVEs. pip install mcp-config-guard
ai-safety claude-code linter mcp model-context-protocol owasp python sarif security vulnerability-scanner
Python
🤖 Team onboarding kit for Claude Code AI coding assistant. Pre-configured with agents, skills, slash commands, and MCP integrations for Java 21/Spring Boot WebFlux, Angular, Flutter, PostgreSQL, and Firebase. Clone → install → start building.
PLpgSQL Python Shell
Educational/Research companion: Security vulnerabilities in AI coding assistants (Claude, Cursor, Copilot) - CVEs, supply chain attacks, trust boundaries
Dockerfile Shell Jupyter Notebook Python
A tremendous feat of documentation, this guide covers Claude Code from beginner to power user, with production-ready templates for Claude Code features, guides on agentic workflows, and a lot of great learning materials, including quizzes and a handy "cheatsheet". Whether it's the "ultimate" guide to Claude Code will be up to the reader :)
agentic-coding ai-assistant ai-coding ai-pair-programming anthropic best-practices claude claude-code cli-tool coding-assistant developer-tools llm mcp-servers tutorial ai-security claude-code-guide cursor-alternative prompt-engineering vibe-coding claude-code-tutorial
JavaScript Shell Python TypeScript
Real-time security layer protecting AI Agents from Confused Deputy attacks, malicious MCP payloads, and Indirect Prompt Injection.
ai rag-pipeline security mcp-client mcp agentic-ai ai-security firewall llm-security mcp-security model-context-protocol prompt-injection rug-pull tool-poisoning
Python YARA
A Security-centric MCP Server providing enterprise-grade filesystem powers to AI assistants—read, write, edit, and manage files with comprehensive CVE protection and user-controlled access.. [Explore comprehensive code documentation and architecture details on DeepWiki](https://deepwiki.com/n0zer0d4y/vulcan-file-ops)
batch-operations code-analysis code-generation filesystem shell-execution vibe-coding dynamic-directory-access secure-mcp selective-tool-activation mcp-server model-context-protocol docx-generation pdf-generation developer-tools
JavaScript TypeScript Dockerfile
None
MCP Guardian Enterprise is an advanced security platform for MCP servers, powered by Naptha AI’s autonomous agent framework. It delivers comprehensive, scalable vulnerability scanning, threat intelligence, and automated remediation. The modular architecture covers runtime, network, secrets, IaC, compliance, and more for enterprise-grade protection.
JavaScript HTML
A collection of Vulnerability Research and Reverse Engineering writeups.
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2025-53109 vulnerability anywhere in the article.
-
The Hacker News
5 Threats That Reshaped Web Security This Year [2025]
As 2025 draws to a close, security professionals face a sobering realization: the traditional playbook for web security has become dangerously obsolete. AI-powered attacks, evolving injection techniqu ... Read more
-
Kaspersky
Security risks of vibe coding and LLM assistants for developers
Although the benefits of AI assistants in the workplace remain debatable, where they’re being adopted most confidently of all is in software development. Here, LLMs play many roles — from refactoring ... Read more
-
Kaspersky
How LLMs can be compromised in 2025 | Kaspersky official blog
Developers of LLM-powered public services and business applications are working hard to ensure the security of their products, but the industry is still in its infancy. As a result, new types of attac ... Read more
-
The Hacker News
Critical mcp-remote Vulnerability Enables Remote Code Execution, Impacting 437,000+ Downloads
Cybersecurity researchers have discovered a critical vulnerability in the open-source mcp-remote project that could result in the execution of arbitrary operating system (OS) commands. The vulnerabili ... Read more
-
Daily CyberSecurity
Anthropic MCP Server Flaws: Path Traversal & Symlink Attacks Allow RCE
Image: Cymulate Cymulate Research Labs has revealed Anthropic’s Filesystem MCP Server vulnerabilities. Two newly disclosed flaws—CVE-2025-53110 and CVE-2025-53109—exposes systems to unauthorized acces ... Read more
-
Cyber Security News
Anthropic’s MCP Server Vulnerability Allowed Attackers to Escape Sandbox and Execute Code
Two high-severity vulnerabilities in Anthropic’s Model Context Protocol (MCP) Filesystem Server enable attackers to escape sandbox restrictions and execute arbitrary code on host systems. The vulnerab ... Read more
The following table lists the changes that have been made to the
CVE-2025-53109 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Jul. 02, 2025
Action Type Old Value New Value Added Description Model Context Protocol Servers is a collection of reference implementations for the model context protocol (MCP). Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files via symlinks within allowed directories. Users are advised to upgrade to 0.6.4 or 2025.7.01 resolve. Added CVSS V4.0 AV:N/AC:L/AT:P/PR:N/UI:P/VC:N/VI:N/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Added CWE CWE-59 Added Reference https://github.com/modelcontextprotocol/servers/commit/d00c60df9d74dba8a3bb13113f8904407cda594f Added Reference https://github.com/modelcontextprotocol/servers/security/advisories/GHSA-q66q-fx2p-7w4m