Zen-Ai-Pentest Framework Skill

Complete guide to the Zen-Ai-Pentest autonomous pentesting framework architecture.

Project Structure

zen-ai-pentest/
├── agents/              # ReAct AI agents (11 specialized personas)
├── api/                 # FastAPI backend + WebSocket
├── core/                # Orchestrator, models, caching
├── tools/               # 72+ integrated security tools
├── risk_engine/         # CVSS, EPSS, false positive detection
├── modules/             # Scanner, exploit modules
├── web_ui/              # React frontend + dashboard
├── database/            # PostgreSQL models (SQLAlchemy)
├── reports/             # PDF/HTML/DOCX generator
├── docker/              # Dockerfiles + compose
├── tests/               # 43,000+ tests (unit, integration, security)
└── mcp/                 # MCP servers (8 total)

Key Components

Agent System

from agents.react_agent import ReActAgent, ReActAgentConfig

config = ReActAgentConfig(max_iterations=10, use_vm=False)
agent = ReActAgent(config)
result = agent.run(target="example.com", objective="Full security assessment")

11 Personas

Persona	CLI	Purpose
Reconnaissance	deep-recon	OSINT, subdomain, port scan
Exploitation	deep-exploit	CVE matching, sandboxed exec
Analysis	deep-analyze	FP detection, CVSS scoring
Reporting	deep-report	PDF/HTML generation
Red Team	deep-redteam	Full adversarial simulation
Social Engineering	deep-social	Phishing, OSINT
Network	deep-network	Infrastructure testing
Cloud	deep-cloud	AWS/Azure/GCP
ICS	deep-ics	SCADA/industrial
Mobile	deep-mobile	iOS/Android
Crypto	deep-crypto	TLS, cert, cipher analysis

Risk Engine

from risk_engine.false_positive_engine import FalsePositiveEngine

engine = FalsePositiveEngine()
score = engine.assess_finding({"vuln_type": "xss", "confidence": 0.85})
# Combines Bayesian + multi-model voting

Guardrails

• Private IP blocking (10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16)
• Risk levels 0-3 (SAFE → AGGRESSIVE)
• Read-only default, --force for exploitation
• Timeout management (10min max)

MCP Servers

# 8 MCP servers registered in opencode.jsonc
mcp/obscura/      # Encrypted secret vault
mcp/ip-tracker/   # Visitor IP tracking
mcp/omni-ai/      # AI chat via OmniRoute
mcp/qterminal/    # Shell/Docker orchestration
mcp/metasploit/   # Metasploit RPC connector
mcp/vpn-killswitch/# Connection-loss failover
mcp/zen-agents/   # 11-agent orchestration