Is the Attack Path Architect skill free?

Yes. The skill itself is free from Orizon-eu/claude-code-pentest. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Attack Path Architect SkillProof Score?

8.0/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.

How do I install Attack Path Architect?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Attack Path Architect with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Attack Path Architect

Turns recon data into MITRE ATT&CK-mapped kill chains, scored and ranked.

by Orizon-eu · Orizon-eu/claude-code-pentest

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 482572f

The two bundled scripts that exist (classify_assets.py, generate_attack_tree.py) really work — ran them on a 3-host fixture and got a genuine MITRE-tagged, feasibility/impact/stealth-scored attack tree (T1190, T1552.005, etc.) far beyond a plain-prose baseline. But Step 5 and Step 7 of the SKILL.md call scripts/find_chains.py and scripts/generate_attack_report.py, which do not exist anywhere in the repo (confirmed 404 on raw GitHub) — the model has to invent chaining analysis and report formatting itself.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 3/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 3/5

What Attack Path Architect does

Classifies recon-discovered assets by exposure/type/risk, maps trust relationships, and generates MITRE ATT&CK-tagged attack trees scored by feasibility/impact/stealth. Triggers on requests for an attack path, kill chain, attack tree, or attack-surface prioritization from recon data or a domain, for authorized pentest/red-team work only.

How to install Attack Path Architect

git clone https://github.com/Orizon-eu/claude-code-pentest
cd claude-code-pentest
mkdir -p ~/.claude/skills
cp -r attack-path-architect ~/.claude/skills/attack-path-architect

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Attack Path Architect

/attack-path-architect Turns recon data into MITRE ATT&CK-mapped kill chains, scored and ranked.

It also activates on plain-language prompts like these:

Generate an attack path from this recon data for our pentest.
Build a MITRE ATT&CK kill chain for this authorized red-team test.
What are the most likely attack paths given this recon JSON?

Frequently asked questions

Is the Attack Path Architect skill free?: Yes. The skill itself is free from Orizon-eu/claude-code-pentest. SkillProof publishes the install command and an independent test verdict at no cost.
Does Attack Path Architect work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. The two bundled scripts that exist (classify_assets.py, generate_attack_tree.py) really work — ran them on a 3-host fixture and got a genuine MITRE-tagged, feasibility/impact/stealth-scored attack tree (T1190, T1552.005, etc.) far beyond a plain-prose baseline. But Step 5 and Step 7 of the SKILL.md call scripts/find_chains.py and scripts/generate_attack_report.py, which do not exist anywhere in the repo (confirmed 404 on raw GitHub) — the model has to invent chaining analysis and report formatting itself.
What is the Attack Path Architect SkillProof Score?: 8.0/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.
How do I install Attack Path Architect?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Attack Path Architect with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.