| name | guardian |
| description | AI-powered penetration testing automation using Guardian CLI with MiniMax as Anthropic API provider |
Guardian Skill
AI-powered penetration testing framework with 19 integrated security tools.
What It Does
- 🤖 Multi-provider AI (OpenAI, Claude, Gemini, OpenRouter)
- 🛠️ 19 Security tools (Nmap, Nuclei, SQLMap, etc.)
- 📊 Evidence capture with full command history
- 🔐 Scope validation (blacklists private networks)
- 📋 Multiple report formats (Markdown, HTML, JSON)
Prerequisites
MiniMax API (Confirmed Compatible!)
MiniMax works as Anthropic API replacement:
export ANTHROPIC_API_KEY="your-minimax-key"
export ANTHROPIC_BASE_URL="https://api.minimax.chat/v1"
Or set in config:
ai:
provider: claude
claude:
model: claude-3-5-sonnet
api_key: ${ANTHROPIC_API_KEY}
base_url: https://api.minimax.chat/v1
Installation
git clone https://github.com/zakirkun/guardian-cli.git
cd guardian-cli
pip install -e .
python -m cli.main --help
python -m cli.main models
Optional Tools
| Tool | Install |
|---|
| nmap | apt install nmap |
| httpx | go install github.com/projectdiscovery/httpx/cmd/httpx@latest |
| subfinder | go install github.com/projectdiscovery/subfinder/v2/cmd/subfinder@latest |
| nuclei | go install github.com/projectdiscovery/nuclei/v3/cmd/nuclei@latest |
| gobuster | go install github.com/OJ/gobuster/v3@latest |
Usage
Quick Commands
python -m cli.main workflow list
python -m cli.main models
python -m cli.main workflow run --name web_pentest --target example.com
python -m cli.main workflow run --name network --target YOUR_INTERNAL_NETWORK
python -m cli.main report --session SESSION_ID --format html
Available Workflows
| Workflow | Purpose |
|---|
web_pentest | Web application security |
network | Network penetration test |
recon | reconnaissance |
autonomous | Full autonomous test |
Target Your Repos
python -m cli.main workflow run --name web_pentest --target https://open-mushaf.vercel.app
python -m cli.main workflow run --name web_pentest --target https://api.open-tarteel.com
python -m cli.main workflow run --name web_pentest --target http://localhost:3000 --repo /path/to/repo
Configuration
Edit config/guardian.yaml:
ai:
provider: claude
claude:
model: claude-3-5-sonnet
api_key: ${ANTHROPIC_API_KEY}
base_url: https://api.minimax.chat/v1
temperature: 0.2
max_tokens: 8000
pentest:
safe_mode: true
require_confirmation: true
max_parallel_tools: 3
max_depth: 3
output:
format: markdown
save_path: ./reports
verbosity: normal
scope:
blacklist:
- 127.0.0.0/8
- 10.0.0.0/8
- YOUR_PRIVATE_SUBNET
Example: Test Your Web Apps
open-mushaf
python -m cli.main workflow run --name web_pentest \
--target https://open-mushaf.vercel.app \
--provider claude
open-tarteel
python -m cli.main workflow run --name web_pentest \
--target https://open-tarteel.vercel.app \
--provider claude
Reports
Reports saved to ./reports/:
reports/
├── 20260207_120000/
│ ├── session.json
│ ├── agents/
│ ├── prompts/
│ └── deliverables/
│ └── security_assessment_report.md
Cost & Time
- Time: 1-1.5 hours for full scan
- Cost: ~$10-50 with MiniMax (varies)
Troubleshooting
AI Provider Errors
python -m cli.main models
cat config/guardian.yaml | grep -A 5 "ai:"
Tool Not Found
which nmap
which httpx
Workflow Not Loading
ls workflows/
python -c "import yaml; yaml.safe_load(open('workflows/web_pentest.yaml'))"
Safety Notes
⚠️ Important
- Only test systems you own or have authorization
- Don't run on production without preparation
- Guardian can create/delete data (safe mode enabled by default)
- Always review findings before remediation
Files Created
skills/guardian/
├── SKILL.md # This file
└── scripts/
└── install.sh # Installation script
Related Skills
- github-insights - GitHub analysis
- daily-digest - Daily summary