# Choosing and Running an Agent Sandbox Safely

A two-part playbook. Part one: write a threat model, match isolation to trust, score a shortlist and estimate cost. Part two: network, secret, state, approval, limit, log and incident controls.

Price: $27.00.

## What is included

- A six-line threat model mapped to OWASP LLM risks
- A six-question provider scorecard and a cost method
- Run-time controls for egress, secrets, snapshots and approvals
- An incident procedure and a quarterly retest routine

Also on the [web page](https://agentsandboxes.fyi/store/agent-sandbox-playbook).

> **Check before you choose.** Vendor specs and prices change. Follow the cited source on each listing before you pick a provider.