zakirkun/guardian-cli

Guardian is a production-ready AI-powered penetration testing automation CLI tool that leverages Google Gemini and LangChain to orchestrate intelligent, step-by-step penetration testing workflows while maintaining ethical hacking standards.

What it solves

Guardian 是一個 AI 驅動的滲透測試自動化框架。它以智慧系統取代手動、重複的安全評估，能規劃、執行與分析網路、Web 應用程式與雲端環境的安全測試，同時蒐集完整證據以產出專業報告。

How it works

Guardian 採用多代理架構，包含 Planner、Tool Selector、Analyst 與 Reporter。它可整合多種 AI 供應商（如 OpenAI、Claude、Gemini）來驅動測試流程。系統透過基於 DAG 的工作流引擎執行超過 50 種整合安全工具（如 nmap、nuclei、sqlmap）。為提升準確度，採用「辯論分流」機制，由三個 AI 角色（Red Advocate、Blue Advocate、Judge）對模糊結果進行辯論，以降低誤報，並使用結合 CVE/CWE/MITRE ATT&CK 資訊的 RAG（檢索增強生成）防止幻覺。

Who it’s for

此框架設計給安全研究人員、授權的滲透測試人員，以及需要自動化複雜安全評估並產出有證據支撐的專業報告的教育環境。

Highlights

  • Multi-Provider AI Support: Compatible with OpenAI, Claude, Gemini, OpenRouter, Requesty, and local models via Ollama.
  • Vision-LLM Triage: Uses headless screenshots and vision-capable LLMs to enrich analysis of web findings.
  • Extensive Toolset: Integrates 50+ security tools across categories like Network, Web Recon, Cloud/Container, and LLM Red-Teaming.
  • Smart Workflow DSL: Supports parallel execution, conditional steps, and session resumption via a DAG scheduler.
  • Professional Reporting: Exports findings to SARIF, DefectDojo, and Slack, including CVSS v3.1 recomputation and AI decision traces.
  • Security Guardrails: Includes DNS-resolve scope validation, prompt-injection defense, and a confirmation gate for intrusive tools.