Guide Intermediate
Claude Code Security Checklist for Teams
A Claude Code security checklist for teams: permission modes, secret deny rules, the Bash sandbox, guard hooks, MCP and plugin review, CI and managed settings.
#security
9 resources tagged “security”.
-
- Recipe Smoke tested
Safe Mode: Block Destructive Commands in Claude Code
A free Claude Code hook kit that denies rm -rf on broad paths and curl | sh, and asks before force-pushes, hard resets and DROP TABLE. It fails closed.
Tested 2 min setup - Guide Beginner
Anthropic API Key: Get, Store and Rotate It Safely
How to get an Anthropic (Claude) API key in the Claude Console, store it in env vars, scope it to a workspace, rotate it and fix 401, 403 and 429 errors.
- Guide Intermediate
Block Dangerous Commands in Claude Code with PreToolUse Hooks
Stop rm -rf, curl | sh, force-pushes and DROP TABLE before they run: a tested PreToolUse hook for Claude Code, deny rules, onFailure and the limits to know.
- Guide Intermediate
Claude Code --dangerously-skip-permissions: When It's Safe
What --dangerously-skip-permissions does in Claude Code, what still stops it, and how to run it safely in a container as a non-root user. Checked October 2026.
- Guide Intermediate
Claude Code Sandbox: Set Up /sandbox for Safer Bash Commands
Turn on the Claude Code sandbox with /sandbox: what it blocks, auto-allow vs regular mode, allowWrite, allowedDomains, credentials and strict mode explained.
- Skill Security
Trail of Bits Skills: Security Auditing for Claude Code
Trail of Bits' skills marketplace adds 46 security plugins to Claude Code: code auditing, static analysis, smart contracts, fuzzing and verification. Setup.
★ 7,762 - Tool Plugin
CC Safety Net: Block Destructive Commands in Claude Code
CC Safety Net is a Claude Code plugin hook that blocks destructive commands like git reset --hard and rm -rf, plus access to secrets, before a tool call runs.
★ 1,768 - Tool Plugin
Security Guidance Plugin: Security Review for Claude Code
security-guidance reviews Claude-generated code in three layers: pattern warnings on edits, an LLM diff review on Stop and an agentic review on git commit.