a9c36fc852
feat: add 3 subagent hooks components (security theme)
...
- hooks/security/ai-bash-guard: PreToolUse with type:agent — AI-powered bash security guard using haiku subagent
- settings/hooks/subagent-lifecycle-logger: SubagentStart/SubagentStop audit trail to .claude/agent-log.jsonl
- agents/security/read-only-auditor: security auditor with frontmatter hooks blocking Write/Edit/Bash while active
2026-05-08 20:27:16 -04:00
aa977104c9
fix: address P1 review issues from cubic-dev-ai
...
1. Python one-liner: detect version-suffixed executables (python3.11, python3.12)
Pattern: python[23]? → python[23]?(\.[0-9]+)?
2. Pipe-to-shell: detect shell invocations with arguments (| sh -s, | bash -c)
Pattern: \|\s*(sh|bash|zsh)\s*$ → (\s|$)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-13 20:44:36 +09:00
5299c0c18d
Add shell-wrapper-guard hook to security category
...
Detects destructive commands hidden in shell wrappers (sh -c, bash -c,
python3 -c, node -e, etc). Complements dangerous-command-blocker by
catching 8 bypass vectors that evade direct command checks.
From cc-safe-setup (667 hooks, 9,200+ tests, 800hrs autonomous operation).
https://github.com/yurukusa/cc-safe-setup
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-13 17:45:08 +09:00
36fa6dbd5d
feat: Add supply-chain-guard skill, worktree commands, security hooks, and updated catalog
...
New components:
- supply-chain-guard skill (security): npm/PyPI/CI supply chain scanner with IOC database
- worktree-guide skill: parallel development with git worktrees
- dependabot-review skill: automated Dependabot PR management
- worktree-check/cleanup/deliver/init commands (git-workflow)
- edit-audit-log hook (development-tools)
- env-file-protection and force-push-blocker hooks (security)
Also includes:
- Regenerated components.json catalog (docs + dashboard)
- TinyFish featured page updates and logo
- .vercelignore and dashboard .gitignore updates
2026-03-31 21:13:20 -04:00
a0b4da050c
fix: dangerous-command-blocker hook references wrong script path ( #367 )
...
The installer (`installIndividualHook` in index.js) places companion
Python scripts in `.claude/hooks/`, but the hook config referenced
`.claude/scripts/`. This meant the hook would always fail with a
"file not found" error at runtime, silently rendering it non-functional.
Also removed the `2>&1` stderr redirect which masked the error by
merging stderr into stdout, causing the hook runner to report the
unhelpful "No stderr output" message instead of the actual cause.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-22 21:17:44 -08:00
d3ce23847f
feat: improve secret-scanner hook with stdin JSON parsing
...
- Update description to list 30+ supported providers
- Simplify hook command by removing git commit grep filter
- Parse Claude Code JSON input from stdin to detect git commit
- Handle git commit -a and chained git add && git commit scenarios
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-28 20:21:52 -05:00
b5c377ae6c
feat: expand secret scanner patterns and add skills support
...
- Add 25+ new secret detection patterns to secret-scanner.py (Anthropic,
Google OAuth, GitLab, Vercel, Supabase, Hugging Face, Replicate, Groq,
Databricks, Azure, Cloudflare, DigitalOcean, Linear, Notion, Figma,
npm, PyPI tokens)
- Fix regex escaping in security-scanner.json (single quote matching)
- Add skills component type to Discord bot interactions
- Add Linear MCP server to .mcp.json
- Update .gitignore for opsx commands, skills, and openspec dirs
- Regenerate components.json catalog
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-28 19:13:48 -05:00
2f667130ad
feat: Add secret-scanner hook for detecting hardcoded credentials ( #304 )
...
Added new security hook that automatically scans staged files before git commits to detect:
- API keys (AWS, OpenAI, Stripe, Google, GitHub, SendGrid, Twilio, Mailgun)
- Authentication tokens and passwords
- Private keys (RSA, SSH, OpenSSH)
- Database connection strings (MySQL, PostgreSQL, MongoDB, SQL Server)
- JWT tokens, Slack tokens, Telegram bot tokens, Discord webhooks
Features:
- Multi-pattern regex detection with severity levels (critical, high, medium, low)
- Excludes false positives from comments with "example" or "placeholder"
- Skips binary files, lock files, and excluded directories
- Provides clear error messages with fix suggestions
- Suggests environment variables and secrets management services
Files:
- cli-tool/components/hooks/security/secret-scanner.json
- cli-tool/components/hooks/security/secret-scanner.py
Co-authored-by: Claude <noreply@anthropic.com >
2026-01-24 18:07:22 -05:00
ceb3a9e40c
feat(hooks): enhance dangerous-command-blocker with multi-level security ( #281 )
...
Enhanced the dangerous-command-blocker hook with comprehensive protection:
## Features:
- **3-Level Security System:**
- Level 1: Block catastrophic commands (rm -rf /, dd, mkfs, fork bombs)
- Level 2: Protect critical paths (.claude/, .git/, node_modules/, .env, etc.)
- Level 3: Warn about suspicious patterns (wildcards, chained commands)
- **Python Script Architecture:**
- Moved from inline Python to dedicated script for better maintainability
- Script auto-installed to .claude/scripts/dangerous-command-blocker.py
- Clear regex patterns and detailed error messages
- **Protected Resources:**
- Claude Code configuration (.claude/)
- Git repository (.git/)
- Node.js dependencies (node_modules/, package.json, package-lock.json)
- Environment files (.env, .env.local, etc.)
- Language manifests (Cargo.toml, go.mod, requirements.txt, Gemfile, composer.json)
## Testing:
- 16/16 test cases passing (100%)
- Blocks catastrophic operations
- Protects critical project files
- Warns on suspicious patterns
- Allows safe operations
Co-authored-by: Claude <noreply@anthropic.com >
2026-01-17 23:10:35 -05:00
5d4f4f1ac0
feat(hooks): add dangerous-command-blocker security hook ( #279 )
...
Add new security hook to prevent accidental execution of dangerous shell
commands like rm -rf, dd, mkfs, and other destructive operations.
Features:
- Blocks rm with dangerous flags (recursive, force) on critical paths
- Detects wildcards and system directory targets (/, ~, *)
- Prevents disk operations (dd, mkfs, format)
- Blocks fork bombs and direct disk device access
- Provides clear safety guidelines in error messages
- Allows safe operations (e.g., rm -rf /tmp/specific-folder)
Reviewed by component-reviewer agent.
Co-authored-by: Claude <noreply@anthropic.com >
2026-01-17 22:37:14 -05:00
c98ce4ec6e
🔧 Fix hook JSON structure for Claude Code compatibility
...
- Update all 14 hooks to use proper Claude Code array/matcher format
- Fix CLI merge logic to handle new hook structure correctly
- Add support for both old and new hook formats during migration
- Remove conflict detection for hooks (Claude Code arrays support multiple entries)
- Ensure hooks follow proper structure:
{
"hooks": {
"EventName": [
{
"matcher": "ToolPattern",
"hooks": [
{"type": "command", "command": "bash-command"}
]
}
]
}
}
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-08-14 07:52:08 -04:00
bea1cd00d4
🪝 Reorganize hooks into thematic categories
...
- Restructure hooks to match component categories (development-tools, git-workflow, testing, automation, security, performance)
- Create 14 new hooks organized by practical use cases:
• Development tools: command logging, file backup, change tracking, formatting, linting
• Git workflow: auto-staging, smart commits
• Testing: automated test running
• Automation: build triggers, notifications, dependency checking
• Security: file protection, vulnerability scanning
• Performance: system monitoring
- Update components.json with new hook structure
- Improve frontend filter consistency across all component types
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-08-13 22:51:15 -04:00
Dani