claude-guardrails

claude-guardrails

Hardened security configuration for Claude Code — deny rules, hooks, and prompt injection defense out of the box.

Why This Exists

Claude Code can read your filesystem, run shell commands, and fetch URLs autonomously. A poisoned file in a cloned repo can hijack its behavior via prompt injection. A careless tool call can leak your SSH keys or .env secrets. These configs add defense-in-depth so you don't have to think about it on every session.

Full vs Lite

Quick Start

The script merges into your existing ~/.claude/settings.json (backing it up first) and is safe to run repeatedly.

Install from source (git clone)

Manual installation

If you prefer to install manually, see full/SETUP.md for step-by-step instructions. The key steps are:

1. Copy the variant's settings.json to ~/.claude/settings.json (or merge permissions.deny and hooks.PreToolUse arrays into your existing config)
2. Append the variant's CLAUDE-security-section.md to ~/.claude/CLAUDE.md
3. Copy patterns/secrets.json to ~/.claude/hooks/patterns/secrets.json (shared pattern list for the two scanners below)
4. Copy scan-secrets.sh to ~/.claude/hooks/scan-secrets/ and add the UserPromptSubmit hook entry to settings
5. Copy scan-commit.sh to ~/.claude/hooks/scan-commit/ (its PreToolUse hook entry is already in the variant's settings.json)
6. (Full only) Copy prompt-injection-defender.sh to ~/.claude/hooks/prompt-injection-defender/ and add the PostToolUse hook entry to settings

Uninstall

Uninstall from source

The uninstall uses a surgical remove approach — it reads the variant's config to identify exactly which deny rules and hooks were added, then subtracts only those entries from your ~/.claude/settings.json. Your own custom rules, hooks, and other settings are left untouched. It…