@ahmetcantryk
7 min read
Agentjacking: The New AI Agent Attack Class
Agentjacking hijacks AI coding agents through poisoned telemetry pulled via MCP. Here is the real threat model and an evergreen defense checklist.
Tag
Agentjacking hijacks AI coding agents through poisoned telemetry pulled via MCP. Here is the real threat model and an evergreen defense checklist.
Model Context Protocol explained for 2026: MCP is now a Linux Foundation standard, and the July release candidate deletes the stateful session you learned.