Security Research Lab

Security research for the age of AI agents.

AI agents run as you, with your credentials, reading your files. We build the tools that stop them from being weaponized against you. Open-source, OS-layer, no magic.

Recent Writing

All posts →

Why Your AI Agent Needs a Firewall

Claude Code runs as you. One malicious prompt is all it takes to wipe your files or exfiltrate your secrets. Here's why OS-layer interception is the only real defense.

Mar 15, 2025

Canary Tokens for the Agentic Era

Traditional canary tokens detect human intruders. Snare is built for a world where the intruder is an AI agent with your credentials.

Feb 28, 2025

The Attack Surface of Agentic Systems

A taxonomy of how AI agents get compromised — from prompt injection to tool poisoning to supply chain attacks on agent workflows.

Jan 10, 2025

Tools

rampart open source

↗

Firewall for AI agents. Intercepts at the OS layer — blocks exfiltration, restricts tool calls, enforces policy before execution.

brew install peg/tap/rampart

snare open source

↗

Canary tokens for AI agents. Plant tripwires in secrets and files. Get alerted the moment an agent touches something it shouldn't.

curl -fsSL https://snare.sh/install | sh