Paths Subjects Questions Quizzes Pricing Search
AI Engineering Advanced Pro

Claude Code Sandboxing and Security

Threat modeling, isolation, and hardening for an agent that can run shell commands

30 min read 6 views

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)

  • 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
    View →
See all 8 questions →

We use cookies for product analytics to improve OmniAtlas. See our Privacy Policy.