Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
Researchers at ASSET Research Group have disclosed a new attack technique, dubbed GhostSplice, that exploits the Model Context Protocol (MCP) to trick…
Tag: Model Context Protocol
SASE Has an AI Blind Spot: Why Packet Inspection Falls Short in Modern Enterprise Security
For years, routing traffic through cloud proxies was sufficient for enterprise security. However, the shift to browser-based work, SaaS applications, and generative…
AI in the Build Pipeline: How Software Supply Chain Security Must Evolve
Software supply chain security was already complex, but the integration of AI into the build pipeline has introduced new risks that traditional…
Microsoft Warns Poisoned MCP Tool Descriptions Can Make AI Agents Leak Data
Microsoft has issued a warning about a new attack vector targeting AI agents that use the Model Context Protocol (MCP). Attackers can…
Model Context Protocol: Standardized Agent Communication
The Model Context Protocol (MCP) by Anthropic is a standardized protocol for agent orchestration, tool calling, and inter-agent communication, simplifying the deployment…
Guardian Agents: Governing AI Identity in Enterprise Environments
AI agents are increasingly deployed in enterprise environments, inheriting permissions and executing tasks autonomously, often bypassing traditional identity governance controls. This article…
Agentjacking Attack Tricks AI Coding Agents Into Running Malicious Code
Cybersecurity researchers at Tenet Security have identified a new class of attack called Agentjacking, which tricks AI coding agents into executing arbitrary…