Menu
Blog How it works Use Cases
agentsh
Open-source runtime for AI agent security
Beacon
AI endpoint visibility and control
Watchtower
Enterprise control plane for agentsh and Beacon
Contact Us

Tagged: vulnerability-research

1 post

← All posts
19 min read

A Year of AI Tool Exploits, One Root Cause

Fourteen vulnerabilities across Claude Code, Cursor, MCP servers, and Claude Desktop share a single root cause: untrusted content driving privileged actions with no independent enforcement layer.