Agent Security Hooks
Description
Security hooks for AI coding assistants (Claude Code, Cursor, Gemini CLI) - block dangerous commands, protect files, audit logsSecurity hooks for AI coding assistants (Claude Code, Cursor, Gemini CLI) - block dangerous commands, protect files, audit logs
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
Agent Security Hooks
[](https://opensource.org/licenses/Apache-2.0) [](https://www.python.org/downloads/)
A Python-based security monitoring system that integrates with AI coding assistant hooks to validate commands against blacklists, block dangerous operations, and log all activities for compliance auditing.
**Designed for Safety**: Built with a "fail-closed" architecture, security-conscious defaults, and sensitive data redaction to prevent accidental operations or data leaks by AI agents.
Table of Contents
- Supported Platforms
- Features
- Architecture
- Installation
- Configuration
- Audit Logs
- CLI Reference
- Security Controls
- Development
- Troubleshooting
- FAQ
- Contributing
- Security
- License
- References
Supported Platforms
| Platform | Config File | Documentation |
|---|---|---|
| Claude Code | .claude/settings.json |
code.claude.com/docs/en/hooks |
| Cursor | .cursor/hooks.json |
cursor.com/docs/agent/hooks |
| Gemini CLI | .gemini/settings.json |
geminicli.com/docs/hooks |
Features
- Command Validation - Block dangerous shell commands (
rm -rf,kubectl delete cluster, etc.) - File Protection - Prevent access to sensitive files (
.env,secrets/,*.pem, etc.) - Confirmation Prompts - Require approval for risky operations (
kubectl apply,git push, etc.) - Audit Logging - JSON Lines logs for compliance and forensics
- Multi-Platform - Single tool works
Related Skills
Defense in Depth
Implement multi-layered testing and security best practices.
SecLists Official Repository
[OWASP Testing Guide](https://owasp.org/www-project-web-security-testing-guide/)
Threat Hunting with Sigma Rules
Use Sigma detection rules to hunt for threats and analyze security events
Maintenance Walkthrough - 2026-03-29
- Re-triaged the full 2026-03-15 security finding set against current `main` and wrote a fresh current-head re
Google Workspace Model Armor
Filter user-generated content for safety
Google Workspace Alert Center
Manage security alerts