# Guardrail Hooks Design

**Date:** 2025-01-06
**Status:** Approved

## Overview

PreToolUse guardrail hooks that prevent dangerous operations by intercepting Bash, Write, and Edit tool calls before execution.

### Goals

- Prevent catastrophic operations (destructive file ops, dangerous system commands, infrastructure mistakes)
- Contextual response: hard block for severe threats, confirmation for moderate risks
- Path-aware: operations inside projects are more permissive than outside
- Auditable: log all interventions for review

### Non-Goals

- Git command guardrails (future consideration)
- Rate limiting or resource protection
- Workflow compliance enforcement

## Architecture

```
~/.claude/
├── hooks/
│   └── hooks.json                    # Hook registration (add PreToolUse)
├── hooks/scripts/
│   ├── guardrail.py                  # Main PreToolUse logic
│   └── guardrail-confirm.py          # Adds operation to session allowlist
├── state/
│   ├── guardrails.json               # Rules configuration
│   └── guardrail-session.json        # Session allowlist (cleared on session end)
└── logs/
    └── guardrail.jsonl               # Audit log (blocked/confirmed only)
```

### Flow

1. Claude invokes Bash/Write/Edit
2. `guardrail.py` runs via PreToolUse hook
3. Check session allowlist - if present, allow
4. Evaluate rules + path context - decide action
5. Allow: return `{"decision": "allow"}`
6. Block/Confirm: log, return `{"decision": "block", "reason": "..."}`
7. For confirm: user approves, Claude calls `guardrail-confirm.py`, retries

## Configuration

**Location:** `~/.claude/state/guardrails.json`

```json
{
  "version": 1,
  "safe_paths": [
    "~/.claude",
    "~/projects"
  ],
  "blocked_paths": [
    "/etc", "/usr", "/var", "/boot", "/sys", "/proc",
    "~/.ssh", "~/.gnupg", "~/.aws"
  ],
  "rules": {
    "bash": [
      {"pattern": "rm -rf /", "action": "block"},
      {"pattern": "rm -rf ~", "action": "block"},
      {"pattern": "rm -rf \\*", "action": "block"},
      {"pattern": "chmod -R 777", "action": "block"},
      {"pattern": ":(){ :|:& };:", "action": "block"},
      {"pattern": "mkfs\\.", "action": "block"},
      {"pattern": "dd if=.* of=/dev/", "action": "block"},
      {"pattern": "> /dev/sda", "action": "block"},
      {"pattern": "shutdown", "action": "confirm"},
      {"pattern": "reboot", "action": "confirm"},
      {"pattern": "systemctl (stop|disable|mask)", "action": "confirm"},
      {"pattern": "rm ", "action": "confirm", "outside_safe_paths": true},
      {"pattern": "kubectl delete", "action": "confirm"},
      {"pattern": "docker rm", "action": "confirm"}
    ],
    "write": [
      {"path_patterns": ["blocked_paths"], "action": "block"},
      {"path_patterns": ["outside_safe_paths"], "action": "confirm"}
    ],
    "edit": [
      {"path_patterns": ["blocked_paths"], "action": "block"},
      {"path_patterns": ["outside_safe_paths"], "action": "confirm"}
    ]
  }
}
```

### Key Concepts

- `pattern`: regex matched against command/path
- `action`: `block` (hard stop) or `confirm` (require approval)
- `outside_safe_paths`: rule only applies when target is outside safe directories
- Bash rules check command string; Write/Edit rules check file path

## Safe Paths Logic

**Evaluation order (first match wins):**

1. **Blocked paths check** - Is target in `blocked_paths`?
   - Yes: apply block/confirm regardless of other factors
   - Protects system-critical locations absolutely

2. **Explicit allowlist** - Is target under a `safe_paths` entry?
   - Yes: path is safe
   - Supports glob patterns (`~/projects/*`)

3. **Git-aware detection** - Is target inside a git repository?
   - Walk up from target path looking for `.git` directory
   - Found: treat as safe (it's an intentional project)

4. **Default** - Path is outside safe areas
   - Operations here trigger `outside_safe_paths` rules

### Path Normalization

- Expand `~` to actual home directory
- Resolve symlinks to real paths
- Handle relative paths by resolving against CWD

### Examples

| Target Path | Result | Reason |
|-------------|--------|--------|
| `/etc/hosts` | blocked/confirm | In `blocked_paths` |
| `~/.ssh/config` | blocked/confirm | In `blocked_paths` |
| `~/.claude/hooks/test.py` | safe | In `safe_paths` |
| `~/projects/myapp/src/main.py` | safe | In `safe_paths` |
| `~/random-repo/file.txt` | safe | Git repo detected |
| `~/Downloads/file.txt` | outside | No match, triggers rules |

**Edge case:** If a git repo exists under a blocked path (unlikely), blocked path wins.

## Hook Implementation

### Registration

Add to `~/.claude/hooks/hooks.json`:

```json
{
  "PreToolUse": [
    {
      "matcher": "Bash|Write|Edit",
      "hooks": [
        {
          "type": "command",
          "command": "~/.claude/hooks/scripts/guardrail.py",
          "timeout": 5
        }
      ]
    }
  ]
}
```

### Hook Input (stdin)

```json
{
  "tool_name": "Bash",
  "tool_input": {
    "command": "rm -rf ~/Downloads/old-project"
  }
}
```

### Hook Output (stdout)

Allow:
```json
{"decision": "allow"}
```

Block:
```json
{
  "decision": "block",
  "reason": "GUARDRAIL BLOCKED: 'rm' outside safe paths.\nTarget: ~/Downloads/old-project\nRule: rm_outside_safe\n\nTo proceed, confirm with user then run:\npython ~/.claude/hooks/scripts/guardrail-confirm.py 'rm -rf ~/Downloads/old-project'"
}
```

## Confirmation Flow

1. **Guardrail blocks** with detailed message including confirm command
2. **Claude reports** to user, asks for confirmation
3. **User confirms** in conversation
4. **Claude runs confirm script:**
   ```bash
   python ~/.claude/hooks/scripts/guardrail-confirm.py "rm -rf ~/Downloads/old-project"
   ```
5. **Confirm script** adds to session allowlist
6. **Claude retries** the original command
7. **Guardrail checks allowlist** - finds match - allows

### Session Allowlist

**Location:** `~/.claude/state/guardrail-session.json`

```json
{
  "confirmed": [
    {"tool": "Bash", "operation": "rm -rf ~/Downloads/old-project", "ts": "2025-01-06T10:24:00"}
  ]
}
```

**Cleanup:** `session-end.sh` clears this file so confirmations don't persist across sessions.

**Matching:** Exact match on tool + operation string.

## Logging

**Location:** `~/.claude/logs/guardrail.jsonl`

**Format:** JSON Lines (append-only)

**Logged events:**
- Every `block` action
- Every `confirm` action (required approval)
- When confirmed operation is allowed

### Log Entry Structure

```json
{"ts": "2025-01-06T10:23:45", "tool": "Bash", "operation": "rm -rf /", "action": "block", "rule": "rm_rf_root", "path_context": "n/a"}
{"ts": "2025-01-06T10:24:01", "tool": "Bash", "operation": "rm ~/Downloads/old", "action": "confirm_required", "rule": "rm_outside_safe", "path_context": "outside"}
{"ts": "2025-01-06T10:24:30", "tool": "Bash", "operation": "rm ~/Downloads/old", "action": "confirmed_allow", "rule": "session_allowlist"}
```

### Fields

- `ts`: ISO 8601 timestamp
- `tool`: Bash, Write, or Edit
- `operation`: Command or file path
- `action`: `block`, `confirm_required`, or `confirmed_allow`
- `rule`: Which rule triggered
- `path_context`: `safe`, `outside`, `blocked`, or `n/a`

## Implementation Checklist

- [ ] Create `state/guardrails.json` with starter rules
- [ ] Create `hooks/scripts/guardrail.py` main logic
- [ ] Create `hooks/scripts/guardrail-confirm.py` confirm helper
- [ ] Modify `hooks/hooks.json` to add PreToolUse registration
- [ ] Modify `hooks/scripts/session-end.sh` to clear session allowlist
- [ ] Create `logs/` directory
- [ ] Test: block scenario (catastrophic command)
- [ ] Test: confirm scenario (rm outside safe paths)
- [ ] Test: allow scenario (operation in safe path)
- [ ] Test: git-aware detection

## Starter Rules

| Category | Pattern | Action |
|----------|---------|--------|
| Catastrophic | `rm -rf /`, `rm -rf ~`, `mkfs.*`, `dd.*of=/dev/` | block |
| Fork bomb | `:(){ :\|:& };:` | block |
| Dangerous chmod | `chmod -R 777` | block |
| System commands | `shutdown`, `reboot` | confirm |
| Service control | `systemctl (stop\|disable\|mask)` | confirm |
| Destructive outside safe | `rm ` (outside safe paths) | confirm |
| K8s destructive | `kubectl delete` | confirm |
| Docker destructive | `docker rm`, `docker system prune` | confirm |
| Write to blocked paths | Any Write/Edit to `/etc`, `~/.ssh`, etc. | block |
| Write outside safe | Any Write/Edit outside safe paths | confirm |