Cursor
Keeping Cursor's agent from running risky commands against real systems.
Cursor's agent can run terminal commands and edit files on its own, depending on the run mode you choose. These guides cover its modes, allow lists and hooks, and how to keep it away from production data and infrastructure.
-
Claude Code vs Cursor: safety controls compared
How Claude Code and Cursor handle approvals, allow and deny rules, sandboxing, hooks and team policy, side by side and checked against both vendors' docs.
Browse by topic
- Claude Code: Running Anthropic's Claude Code safely: hooks, permissions, settings and guardrails.
- Hooks: Using agent hooks to check, warn about or block an action before it runs.
- Permissions: Allow lists, deny lists, approval modes and credentials for coding agents.
- Databases: Protecting production databases from destructive queries and unsafe migrations by AI agents.
- Infrastructure: Keeping agents from deleting or changing cloud infrastructure, Terraform state and Kubernetes resources.
- Incidents: Public incidents where AI coding agents broke something, and what they teach.
- Guardrails: The general practice of putting safety checks between an AI agent and the systems it can change.