Mandu Security

SkillSecurity

Security best practices for Mandu applications. Use when implementing authentication, authorization, input validation, or protecting against common vulnerabilities. Triggers on guard, auth, CSRF, XSS, or security tasks.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Mandu Security skill

What this skill tells your AI

The instructions your AI receives, as published by konamgil/mandu in docs/archive/skills/mcp-v0/mandu-security/SKILL.md and read by ahel’s review.

Mandu 애플리케이션의 보안 모범 사례 가이드. slot guard를 통한 인증/인가, 입력 검증, CSRF/XSS 방어, 환경 변수 관리를 다룹니다.

Agent Workflow Contract

This skill is a Domain addendum. It must not replace mandu-agent-workflow. Use it only after mandu.agent.plan selects security, auth, slot, API, or runtime domains.

Canonical workflow step: plan -> verify -> repair.

Preferred MCP tools:

StepTools
planmandu.agent.plan, mandu.docs.search
applymandu.agent.apply
verifymandu.agent.verify, mandu.guard.check, mandu.contract.validate
repairmandu.agent.repair, mandu.guard.explain

Allowed file edits:

  • Auth/session slot logic named in the plan
  • Server-only validation and security header configuration
  • Environment templates, never secret values

Verification command:

mandu agent verify --changed --json --write

Common failures:

  • Exposing secrets through client bundles or sync artifacts
  • Changing auth behavior without route/API/slot verification
  • Treating guard findings as policy problems before checking source boundaries

Repair path:

mandu agent repair --from .mandu/agent-verify.json --json

When to Apply

Reference these guidelines when:

  • Implementing authentication in slots
  • Adding authorization guards
  • Validating user input
  • Protecting against CSRF/XSS attacks
  • Managing secrets and environment variables
  • Handling sensitive data

Rule Categories by Priority

PriorityCategoryImpactPrefix
1AuthenticationCRITICALsec-auth-
2Input ValidationCRITICALsec-input-
3CSRF/XSS ProtectionHIGHsec-protect-
4Environment & SecretsHIGHsec-env-
5Data HandlingMEDIUMsec-data-

Quick Reference

1. Authentication (CRITICAL)

  • sec-auth-guard - Use guard() for authentication checks
  • sec-auth-session - Secure session management
  • sec-auth-jwt - JWT token handling best practices

2. Input Validation (CRITICAL)

  • sec-input-validate - Always validate and sanitize input
  • sec-input-schema - Use schema validation (Zod, etc.)
  • sec-input-escape - Escape output to prevent injection

3. CSRF/XSS Protection (HIGH)

  • sec-protect-csrf - CSRF token implementation
  • sec-protect-xss - XSS prevention techniques
  • sec-protect-headers - Security headers configuration

4. Environment & Secrets (HIGH)

  • sec-env-management - Environment variable best practices
  • sec-env-no-expose - Never expose secrets to client

5. Data Handling (MEDIUM)

  • sec-data-sanitize - Sanitize data before storage
  • sec-data-encrypt - Encrypt sensitive data

Security Checklist

□ Authentication required for protected routes
□ Input validated on server side
□ Output escaped/sanitized
□ CSRF tokens for state-changing operations
□ Security headers configured
□ Secrets in environment variables only
□ No sensitive data in client bundles

How to Use

Read individual rule files for detailed explanations:

rules/sec-auth-guard.md
rules/sec-input-validate.md
rules/sec-protect-csrf.md

Signals

GitHub stars
46
Forks
3
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
mandu-security
Source
github.com/konamgil/mandu