From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers

The model context protocol MCP standardizes how LLMs connect to external tools and data sources, enabling faster integration but introducing new attack vectors. Despite the growing adoption of MCP, existing MCP security studies classify attacks by their observable effects, obscuring how attacks...

LibreChat 信息泄露漏洞

LibreChat is an open-source, free, and highly customizable unified AI dialogue platform. It allows for the aggregation and running of large models from any vendor within one interface. Versions of LibreChat from 0.8.2-rc1 to 0.8.3-rc1 have a vulnerability related to information leakage. This...

Auditing MCP Servers for Over-Privileged Tool Capabilities

The Model Context Protocol MCP has emerged as a standard for connecting Large Language Models LLMs to external tools and data. However, MCP servers often expose privileged capabilities, such as file system access, network requests, and command execution that can be exploited if not properly...

CVE-2025-69196 FastMCP OAuth Proxy token reuse across MCP servers

FastMCP is the standard framework for building MCP applications. Prior to version 2.14.2, the server does not properly respect the resource parameter submitted by the client in the authorization and token request. Instead of issuing the token explicitly for the MCP server, the token is issued for...

CVE-2025-69196 FastMCP OAuth Proxy token reuse across MCP servers

FastMCP is the standard framework for building MCP applications. Prior to version 2.14.2, the server does not properly respect the resource parameter submitted by the client in the authorization and token request. Instead of issuing the token explicitly for the MCP server, the token is issued for...

GHSA-W5CR-2QHR-JQC5 Cloudflare Agents has a Reflected Cross-Site Scripting (XSS) vulnerability in AI Playground site

Summary A Reflected Cross-Site Scripting XSS vulnerability was discovered in the AI Playground's OAuth callback handler. The errordescription query parameter was directly interpolated into an HTML script tag without proper escaping, allowing attackers to execute arbitrary JavaScript in the contex...

CVE-2026-1721

Summary A Reflected Cross-Site Scripting XSS vulnerability was discovered in the AI Playground's OAuth callback handler. The errordescription query parameter was directly interpolated into an HTML script tag without proper escaping, allowing attackers to execute arbitrary JavaScript in the contex...

CVE-2026-1721 Reflected Cross-Site Scripting (XSS) vulnerability in AI Playground site

Summary A Reflected Cross-Site Scripting XSS vulnerability was discovered in the AI Playground's OAuth callback handler. The errordescription query parameter was directly interpolated into an HTML script tag without proper escaping, allowing attackers to execute arbitrary JavaScript in the contex...

Cloudflare Agents 安全漏洞

Cloudflare Agents is an open-source tool developed by Cloudflare for building and deploying AI agents on Cloudflare platforms. There is a security vulnerability in Cloudflare Agents, which stems from the improper escaping of the errordescription query parameter in the OAuth callback handler of th...

CVE-2026-22792

5ire is a cross-platform desktop artificial intelligence assistant and model context protocol client. Prior to version 0.15.3, an unsafe HTML rendering permits untrusted HTML including on event attributes to execute in the renderer context. An attacker can inject an payload to run arbitrary...

CVE-2026-22792

5ire is a cross-platform desktop artificial intelligence assistant and model context protocol client. Prior to version 0.15.3, an unsafe HTML rendering permits untrusted HTML including on event attributes to execute in the renderer context. An attacker can inject an payload to run arbitrary...

CVE-2026-22792

5ire is a cross-platform desktop artificial intelligence assistant and model context protocol client. Prior to version 0.15.3, an unsafe HTML rendering permits untrusted HTML including on event attributes to execute in the renderer context. An attacker can inject an payload to run arbitrary...

CVE-2026-22792 5ire vulnerable to Remote Code Execution (RCE)

5ire is a cross-platform desktop artificial intelligence assistant and model context protocol client. Prior to version 0.15.3, an unsafe HTML rendering permits untrusted HTML including on event attributes to execute in the renderer context. An attacker can inject an payload to run arbitrary...

EUVD-2026-3778

5ire is a cross-platform desktop artificial intelligence assistant and model context protocol client. Prior to version 0.15.3, an unsafe HTML rendering permits untrusted HTML including on event attributes to execute in the renderer context. An attacker can inject an payload to run arbitrary...

CVE-2026-22792 5ire vulnerable to Remote Code Execution (RCE)

5ire is a cross-platform desktop artificial intelligence assistant and model context protocol client. Prior to version 0.15.3, an unsafe HTML rendering permits untrusted HTML including on event attributes to execute in the renderer context. An attacker can inject an payload to run arbitrary...

PT-2026-3863

Name of the Vulnerable Software and Affected Versions 5ire versions prior to 0.15.3 Description 5ire is a cross-platform desktop artificial intelligence assistant and model context protocol client. Prior to version 0.15.3, unsafe HTML rendering allows untrusted HTML, including on event attributes...

CVE-2026-23744 REC in MCPJam inspector due to HTTP Endpoint exposes

MCPJam inspector is the local-first development platform for MCP servers. Versions 1.4.2 and earlier are vulnerable to remote code execution RCE vulnerability, which allows an attacker to send a crafted HTTP request that triggers the installation of an MCP server, leading to RCE. Since MCPJam...

Deco Apps Library / MCP Servers 代码问题漏洞

Deco Apps Library / MCP Servers is a content management system from deco.cx open source. A code issue vulnerability exists in Deco Apps Library / MCP Servers version 0.120.1 and earlier, which stems from incorrect manipulation of the parameter url in the file website/loaders/analyticsScript.ts,...

Securing MCP Servers with Spring AI

Model Context Protocol, or MCP for short, has taken over the AI world. If you've been following our blog, you've probably read the introduction to the topic, Connect Your AI to Everything: Spring AI's MCP Boot Starters. The security aspects of MCP have been evolving fast, and the latest version o...

CVE-2025-58357 5ire Chat Message XSS Vulnerability Enables Remote Code Execution

5ire is a cross-platform desktop artificial intelligence assistant and model context protocol client. Version 0.13.2 contains a vulnerability in the chat page's script gadgets that enables content injection attacks through multiple vectors: malicious prompt injection pages, compromised MCP server...