#tool-use
tool-use
2 articles tagged with #tool-use
guides
How to Prevent Confused Deputy Attacks in MCP Workflows
The confused deputy problem is the most dangerous attack pattern in AI agent systems using MCP. Here's how it works and how to prevent it.
Akash Mahajan
guides
MCP Security Risks: A Guide for AI Agent Developers
Security risks in Model Context Protocol (MCP) servers — confused deputy attacks, credential leakage, prompt injection through tool outputs, and how to mitigate them.
Akash Mahajan