Claude Code Sandboxing and Security
Threat modeling, isolation, and hardening for an agent that can run shell commands
Learn to reason about Claude Code as a system with a real attack surface: where prompt injection actually enters a session, how the built-in Bash sandbox and dev containers isolate what a command can reach, how permission rules and hooks compose into layered defense, what MCP servers can do outside the sandbox, and what data actually leaves your machine. By the end you'll be able to design a defensible sandbox-plus-permissions policy for a real team, not just recite the individual settings.
Practice questions (8)
-
View →
Tracing a Prompt-Injection Attack Through a Poisoned PR Comment
Advanced · Free -
View →
Designing a Sandbox and Permission Policy for a Fintech Monorepo
Advanced · Free -
View →
When (and When Not) to Use --dangerously-skip-permissions
Advanced -
View →
Vetting an MCP Server and Understanding What Managed MCP Changes
Advanced -
View →
Layered Defense for a 'Never Touch Prod DB' Org Rule
Advanced