guardian-cli
zakirkun/guardian-cli
Guardian is an enterprise-grade, AI-powered penetration testing automation framework that orchestrates specialized AI agents and security tools through customizable YAML workflows.
1.8k 361No licenseUpdated 2026-06-27
61
GoodOverview
Guardian is a Python-based CLI application designed to automate security assessments using a multi-agent AI architecture. It integrates with various large language models and numerous security utilities to plan scans, execute tools, analyze output, and generate comprehensive reports in multiple formats.
Capabilities
- ▸Multi-provider AI integrations including OpenAI, Anthropic, Google, and local models
- ▸Multi-agent architecture featuring planning, tool execution, analysis, and reporting roles
- ▸Execution of 19 integrated security utilities such as nmap, nuclei, sqlmap, and ffuf
- ▸YAML-defined workflow orchestration with parameter overrides
- ▸Session state tracking and vulnerability evidence capture
Best for
Running automated web application and network penetration testing workflows., Conducting reconnaissance and vulnerability sweeps against specified targets., Generating professional Markdown, HTML, and JSON security assessment reports.
Works with
Claude CodeCodexChatGPTGemini CLICursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
61Task usefulness20%88 → +17.6
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%85 → +12.8
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%44 → +5.3
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%15 → +2.3
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%85 → +6.8
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total71.7 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
This tool is intended strictly for authorized security assessments and educational purposes. It includes safe mode options and scope blacklists, but users must ensure explicit permission is obtained prior to execution to avoid legal liabilities.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.