Skills Plugins MCP Prompt Model 博客 我的中心

attack-tree-construction

Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.

DeepseekModel 官方收录技能 质量 优秀 · 90 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=wshobson-agents-plugins-security-scanning-skills-attack-tree-construction-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name attack-tree-construction description Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders. Attack Tree Construction Systematic attack path visualization and analysis. When to Use This Skill Visualizing complex attack scenarios Identifying defense gaps and priorities Communicating risks to stakeholders Planning defensive investments Penetration test planning Security architecture review Core Concepts 1. Attack Tree Structure [Root Goal] | ┌────────────┴────────────┐ │ │ [Sub-goal 1] [Sub-goal 2] (OR node) (AND node) │ │ ┌─────┴─────┐ ┌─────┴─────┐ │ │ │ │ [Attack] [Attack] [Attack] [Attack] (leaf) (leaf) (leaf) (leaf) 2. Node Types Type Symbol Description OR Oval Any child achieves goal AND Rectangle All children required Leaf Box Atomic attack step 3. Attack Attributes Attribute Description Values Cost Resources needed $, $$, $$$ Time Duration to execute Hours, Days, Weeks Skill Expertise required Low, Medium, High Detection Likelihood of detection Low, Medium, High Templates and detailed worked examples Full template library lives in references/details.md . Read that file when you need concrete templates for this skill. Best Practices Do's Start with clear goals - Define what attacker wants Be exhaustive - Consider all attack vectors Attribute attacks - Cost, skill, and detection Update regularly - New threats emerge Validate with experts - Red team review Don'ts Don't oversimplify - Real attacks are complex Don't ignore dependencies - AND nodes matter Don't forget insider threats - Not all attackers are external Don't skip mitigations - Trees are for defense planning Don't make it static - Threat landscape evolves
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。