dangerous-command-blocker

for pattern, desc in critical_paths: if re.search(pattern, cmd, re.IGNORECASE): print(f'🛑 BLOCKED: Critical path protection activated!', file=sys.stderr) print(f'', file=sys.stderr) print(f'Protected resource: {desc}', file=sys.stderr)…

Automations
Security
549

What it does and how to use it

A hook that automates security actions at key moments (before/after a tool runs, on save, etc.), without you having to think about it.

Install the hook (command above).
It runs automatically on the defined events.
Adjust the rules in the settings file if you want to fine-tune it.

Install (Claude Code)

mkdir -p .claude/hooks && curl -fsSL https://doutorai.pt/data/lib/hooks__dangerous-command-blocker.md -o .claude/hooks/dangerous-command-blocker.py

Paste this command into the terminal, in your project folder, and the component installs automatically.

Content

#!/usr/bin/env python3
"""
Dangerous Command Blocker Hook
Multi-level security system for blocking dangerous shell commands
"""

import json
import sys
import re

# Load command from stdin
data = json.load(sys.stdin)
cmd = data.get('tool_input', {}).get('command', '')

# === LEVEL 1: CATASTROPHIC COMMANDS (ALWAYS BLOCK) ===
catastrophic_patterns = [
    (r'\brm\s+.*\s+/\s*$', 'rm on root directory'),
    (r'\brm\s+.*\s+~\s*$', 'rm on home directory'),
    (r'\brm\s+.*\s+\*\s*$', 'rm with star wildcard'),
    (r'\brm\s+-[rfRF]*[rfRF]+.*\*', 'rm -rf with wildcards'),
    (r'\b(dd\s+if=|dd\s+of=/

- 🔒 Full content on the Pro plan (€7.99/month) -

Need help with Claude Code?

Ask Dr AI - it explains things simply.

Need a tailor-made solution?

Not sure where to start with AI in your business? Get a free assessment and a tailored plan - no commitment.

Save hours every week with AI, no hassle

Doutor AI gives you 1,859 ready-to-copy AI prompts, by industry and in plain English - plus a complete technical library for those who want to go further.

See plans