mcpbeat

Attack Tree Construction

dokhacgiakhoa/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.

6k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
505
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI --skill attack-tree-construction

What comes with it

21 937 bytes besides the instruction
sub-skills/implementation-playbook.md

The instruction itself

8 sections, as written by the author

Attack Tree Construction

Systematic attack path visualization and analysis.

Use this skill when

  • Visualizing complex attack scenarios
  • Identifying defense gaps and priorities
  • Communicating risks to stakeholders
  • Planning defensive investments or test scopes

Do not use this skill when

  • You lack authorization or a defined scope to model the system
  • The task is a general risk review without attack-path modeling
  • The request is unrelated to security assessment or design

Instructions

  • Confirm scope, assets, and the attacker goal for the root node.
  • Decompose into sub-goals with AND/OR structure.
  • Annotate leaves with cost, skill, time, and detectability.
  • Map mitigations per branch and prioritize high-impact paths.
  • If detailed templates are required, open resources/implementation-playbook.md.

Safety

  • Share attack trees only with authorized stakeholders.
  • Avoid including sensitive exploit details unless required.

Resources

  • resources/implementation-playbook.md for detailed patterns, templates, and examples.

🧠 Knowledge Modules (Fractal Skills)

1. implementation-playbook

How to use it

Copy the folder

Take dokhacgiakhoa/attack-tree-construction from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.