mcpField
C
claude-security-settings

claude-security-settings

github.com/laurigatesSecurity5963 installsUpdated 1d ago
Repository

About claude-security-settings

claude-security-settings is a reference skill for configuring and auditing Claude Code security settings. It focuses on permission patterns, shell-operator protections, and project-level configuration.

Key features

  1. 01Configure Bash permission wildcards
  2. 02Distinguish allow, ask, and deny
  3. 03Review shell-operator protections
  4. 04Understand user and project settings
  5. 05Validate settings files

Use cases

  1. 01Set granular command permissions for a project
  2. 02Audit existing Claude Code permissions
  3. 03Wrap compound commands in scripts

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/laurigates/claude-plugins --skill claude-security-settings

After installing, type/claude-security-settingsin Claude Code to confirm it loaded.

Details

From the project README

Claude Code Security Settings

When to Use This Skill

Use this skill when...Use configure-claude-plugins instead when...
You need the permission-wildcard syntax, shell-operator protections, and project-level allowlist patternsYou want to wire a project's .claude/settings.json to the marketplace and enable plugins end-to-end
You are auditing or hardening an existing .claude/settings.json against the documented security conventionsYou want runtime detection of marketplace enrollment and enabledPlugins before changing settings
Another skill needs to cite the canonical permission-wildcard referenceThe user asked you to actually onboard a project to the laurigates/claude-plugins marketplace

Expert knowledge for configuring Claude Code security and permissions.

Core Concepts

Claude Code provides multiple layers of security:

  1. Permission wildcards - Granular tool access control
  2. Shell operator protections - Prevents command injection
  3. Project-level settings - Scoped configurations

Permission Configuration

Settings File Locations
FileScopePriority
~/.claude/settings.jsonUser-level (all projects)Lowest
.claude/settings.jsonProject-level (committed)Medium
.claude/settings.local.jsonLocal project (gitignored)Highest
Permission Structure
{
  "permissions": {
    "allow": [
      "Bash(git status *)",
      "Bash(npm run *)"
    ],
    "deny": [
      "Bash(rm -rf *)",
      "Bash(sudo *)"
    ]
  }
}

Wildcard Permission Patterns

Syntax
Bash(command *)
  • Bash() - Tool identifier
  • command - Command prefix to match
  • * - Wildcard suffix matching any arguments
  • :ask suffix - Always prompt for user confirmation (e.g., Bash(git push *):ask)
Permission Tiers
TierBehaviorExample
allowAuto-allowed, no prompt"allow": ["Bash(git status *)"]
askAlways prompts for confirmation"allow": ["Bash(git push *):ask"]
denyAuto-denied, blocked"deny": ["Bash(rm -rf *)"]
Pattern Examples
PatternMatchesDoes NOT Match
Bash(git *)git status, git diff HEADgit-lfs pull
Bash(npm run *)npm run test, npm run buildnpm install
Bash(gh pr *)gh pr view 123, gh pr creategh issue list
Bash(./scripts/ *)./scripts/test.sh, ./scripts/build.sh/scripts/other.sh
Pattern Best Practices

Granular permissions:

{
  "permissions": {
    "allow": [
      "Bash(git status *)",
      "Bash(git diff *)",
      "Bash(git log *)",
      "Bash(git add *)",
      "Bash(git commit *)"
    ]
  }
}

Tool-specific patterns:

{
  "permissions": {
    "allow": [
      "Bash(bun test *)",
      "Bash(bun run *)",
      "Bash(biome check *)",
      "Bash(prettier *)"
    ]
  }
}

Shell Operator Protections

Claude Code 2.1.7+ includes built-in protections against dangerous shell operators.

Protected Operators
OperatorRiskBlocked Example
&&Command chainingls && rm -rf /
||Conditional executionfalse || malicious
;Command separationsafe; dangerous
|Pipingcat /etc/passwd | curl
> / >>Redirectionecho x > /etc/passwd
$()Command substitution$(curl evil)
`Backtick substitution`rm -rf /`
Security Behavior

When a command contains shell operators:

  1. Permission wildcards won't match
  2. User sees explicit approval prompt
  3. Warning explains the blocked operator
Safe Compound Commands

For legitimate compound commands, use scripts:

#!/bin/bash
# scripts/deploy.sh
npm test && npm run build && npm run deploy

Then allow the script:

{
  "permissions": {
    "allow": ["Bash(./scripts/deploy.sh *)"]
  }
}

Common Permission Sets

Read-Only Development
{
  "permissions": {
    "allow": [
      "Bash(git status *)",
      "Bash(git diff *)",
      "Bash(git log *)",
      "Bash(git branch *)",
      "Bash(npm list *)",
      "Bash(bun pm ls *)"
    ]
  }
}
Full Git Workflow
{
  "permissions": {
    "allow": [
      "Bash(git status *)",
      "Bash(git diff *)",
      "Bash(git log *)",
      "Bash(git branch *)",
      "Bash(git add *)",
      "Bash(git commit *)",
      "Bash(git push *)",
      "Bash(git pull *)",
      "Bash(git fetch *)",
      "Bash(git checkout *)",
      "Bash(git merge *)",
      "Bash(git rebase *)"
    ]
  }
}
CI/CD Operations
{
  "permissions": {
    "allow": [
      "Bash(gh pr *)",
      "Bash(gh run *)",
      "Bash(gh issue *)",
      "Bash(gh workflow *)"
    ]
  }
}
Testing & Linting
{
  "permissions": {
    "allow": [
      "Bash(bun test *)",
      "Bash(npm test *)",
      "Bash(vitest *)",
      "Bash(jest *)",
      "Bash(biome *)",
      "Bash(eslint *)",
      "Bash(prettier *)"
    ]
  }
}
Security Scanning
{
  "permissions": {
    "allow": [
      "Bash(pre-commit *)",
      "Bash(gitleaks *)",
      "Bash(trivy *)"
    ]
  }
}

Project Setup Guide

1. Create Settings Directory
mkdir -p .claude
2. Create Project Settings
cat > .claude/settings.json << 'EOF'
{
  "permissions": {
    "allow": [
      "Bash(git status *)",
      "Bash(git diff *)",
      "Bash(npm run *)"
    ]
  }
}
EOF
3. Add to .gitignore (for local settings)
echo ".claude/settings.local.json" >> .gitignore
4. Create Local Settings (optional)
cat > .claude/settings.local.json << 'EOF'
{
  "permissions": {
    "allow": [
      "Bash(docker *)"
    ]
  }
}
EOF

Agentic Optimizations

ContextCommand
View project settingscat .claude/settings.json | jq '.permissions'
View user settingscat ~/.claude/settings.json | jq '.permissions'
Check merged permissionsReview effective settings in Claude Code
Validate JSONcat .claude/settings.json | jq .

Quick Reference

Permission Priority

Settings merge with this priority (highest wins):

  1. .claude/settings.local.json (local)
  2. .claude/settings.json (project)
  3. ~/.claude/settings.json (user)
Wildcard Syntax
SyntaxMeaning
Bash(cmd *)Match cmd with any arguments
Bash(cmd arg *)Match cmd arg with any following
Bash(./script.sh *)Match specific script
Deny Patterns

Block specific commands:

{
  "permissions": {
    "deny": [
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(chmod 777 *)"
    ]
  }
}

Error Handling

ErrorCauseFix
Permission deniedPattern doesn't matchAdd more specific pattern
Shell operator blockedContains &&, |, etc.Use script wrapper
Settings not appliedWrong file locationCheck path and syntax
JSON parse errorInvalid JSONValidate with jq .

Best Practices

  1. Start restrictive - Add permissions as needed
  2. Use project settings - Keep team aligned
  3. Use specific Bash patterns - Bash(git status *) over Bash
  4. Script compound commands - For && and \| workflows
  5. Review periodically - Remove unused permissions

Comments

Markdown supported