بنقرة واحدة
guardian
AI-powered penetration testing automation using Guardian CLI with MiniMax as Anthropic API provider
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
AI-powered penetration testing automation using Guardian CLI with MiniMax as Anthropic API provider
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.
Look up any arxiv paper on alphaxiv.org to get a structured AI-generated overview
Socratic questioning protocol + user communication. MANDATORY for complex requests, new features, or unclear requirements. Includes progress reporting and error handling.
Lighthouse-style efficiency audit for OpenClaw. Scores your instance A+ to F across 6 categories (context injection, cron health, session bloat, config, skills, transcripts). Identifies wasted tokens, bloated sessions, misconfigured crons, and model right-sizing opportunities. Zero dependencies (Python stdlib only).
Make your AI agent learn and improve automatically. Reviews sessions, extracts learnings, updates memory files, and compounds knowledge over time. Set up nightly review loops that make your agent smarter every day.
A multi-agent deliberation hub with 3 core agents and extensible extended agents. Can call user workspace skills when needed.
| name | guardian |
| description | AI-powered penetration testing automation using Guardian CLI with MiniMax as Anthropic API provider |
AI-powered penetration testing framework with 19 integrated security tools.
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
# Clone and install
git clone https://github.com/zakirkun/guardian-cli.git
cd guardian-cli
pip install -e .
# Verify
python -m cli.main --help
python -m cli.main models
| 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 |
# List workflows
python -m cli.main workflow list
# Check AI models
python -m cli.main models
# Run web pentest
python -m cli.main workflow run --name web_pentest --target example.com
# Run network scan
python -m cli.main workflow run --name network --target YOUR_INTERNAL_NETWORK
# Generate report
python -m cli.main report --session SESSION_ID --format html
| Workflow | Purpose |
|---|---|
web_pentest | Web application security |
network | Network penetration test |
recon | reconnaissance |
autonomous | Full autonomous test |
# Test open-mushaf (if deployed)
python -m cli.main workflow run --name web_pentest --target https://open-mushaf.vercel.app
# Test open-tarteel API
python -m cli.main workflow run --name web_pentest --target https://api.open-tarteel.com
# Test local development
python -m cli.main workflow run --name web_pentest --target http://localhost:3000 --repo /path/to/repo
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 # Prevent destructive actions
require_confirmation: true # Confirm before each step
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
python -m cli.main workflow run --name web_pentest \
--target https://open-mushaf.vercel.app \
--provider claude
python -m cli.main workflow run --name web_pentest \
--target https://open-tarteel.vercel.app \
--provider claude
Reports saved to ./reports/:
reports/
├── 20260207_120000/
│ ├── session.json
│ ├── agents/
│ ├── prompts/
│ └── deliverables/
│ └── security_assessment_report.md
# Verify API key
python -m cli.main models
# Check config
cat config/guardian.yaml | grep -A 5 "ai:"
# Install missing tools
which nmap
which httpx
# Check workflow exists
ls workflows/
# Verify YAML syntax
python -c "import yaml; yaml.safe_load(open('workflows/web_pentest.yaml'))"
⚠️ Important
skills/guardian/
├── SKILL.md # This file
└── scripts/
└── install.sh # Installation script