Cross-Server Tool Shadowing: Hijacking Calls Between Servers
Context MCP allows an AI agent to connect to multiple tool servers simultaneously. This flexibility can be dangerous: if one of those […]
Rug Pulls (Silent Redefinition): When Tools Turn Malicious Over Time
Context Imagine that the AI assistant’s tool was actually safe at first – perhaps you used it for days without issue. Then, […]
Secrets in the Wind: Environment Variables, URLs, and the Leaky Abstractions
Context In the evolving landscape of MCP servers and AI agents, a new category of risk is emerging: sensitive data exposure through […]
Tool Poisoning: Hidden Instructions in MCP Tool Descriptions
Imagine installing a seemingly benign math tool on your AI assistant that simply adds two numbers. Unbeknownst to you, the tool’s description […]
MCP Server: The Dangers of “Plug-and-Play” Code
With great power comes great(er) responsibility Since its launch in November 2024, MCP (Model Context Protocol) has been adopted across industries, for […]