Developer Tools

A solid strongbox standing open, with a key still in the lock and a folded note slipped underneath it

Your Agent Doesn't Need to Be Hacked. It Needs to Be Trusted.

Here’s a fact that should change how you think about your agent’s security: in July 2026, security researchers broke out of four widely used AI coding agents — Cursor, Codex CLI, Gemini CLI, and Antigravity — without breaking a single sandbox. Not one of the seven disclosed issues defeated the sandbox directly. Every one of them exploited the same thing instead: a gap between what the sandbox restricts and what a trusted component outside it later reads, runs, or scans. ...

A small cluster of cables plugged into a single hub, one cable visibly frayed, lit in warm amber light

Your Agent Trusts Everything You Connected It To

Most solo builders now run an AI agent with real access: a file system, a couple of API keys, a database, maybe a deploy script. To make it useful, you connected it to things. A server from a README. A config you copied from a blog post. Something that “just worked” in about four minutes. That’s the part worth slowing down on. The thing you actually agreed to An MCP server is not a plugin. When you connect one, you hand the agent a set of tools, and you hand it the schema that describes those tools — their names, their parameters, and their descriptions. The model reads that description and decides when to call it. ...