Active Directory Attack Path logo

Active Directory Attack Path

Organization
zero-lab-ai
active-directory-attack-path

Analyzes and prioritizes Active Directory and BloodHound attack paths using evidence freshness, disabled principals, prerequisites, authorization, operational noise, and remediation coverage. Use during an authorized red-team operation when reviewing AD graphs, nested groups, ACL abuse, delegation, sessions, GPO control, or routes to Tier Zero.

Overview

Publisherzero-lab-ai
Repositoryskills
Skill nameactive-directory-attack-path
Stars
232
Forks
14
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zero-lab-ai on GitHub. Read the source before you install it.

Installation

Install the Active Directory Attack Path AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zero-lab-ai/skills/tree/main/plugins/identity-security/skills/active-directory-attack-path
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zero-lab-ai/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/identity-security/skills/active-directory-attack-path .claude/skills/active-directory-attack-path
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Active Directory Attack Path in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Active Directory Attack Path on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Active Directory Attack Path is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Active Directory attack paths

A graph relationship describes possible control. It does not prove current session state, usable credentials, authorized traversal, or the best route for an operation. Keep those claims separate.

When to Use

  • An authorized red-team operation when reviewing AD graphs, nested groups, ACL abuse, delegation, sessions, GPO control, or routes to Tier Zero.
  • Use only within explicit authorization and the stated rules of engagement.

When NOT to Use

  • Do not treat this skill as permission to access, test, or change a target.
  • Do not convert missing evidence into a clean result or a stronger claim.

Workflow

  1. Confirm the owned starting principals, high-value objectives, allowed evidence reads, allowed traversal actions, and acceptable operational noise.
  2. Inventory relevant users, groups, computers, GPOs, domains, and trusts. Record whether user and computer accounts are enabled and when volatile evidence was collected.
  3. Normalize group membership, administrative rights, object-control rights, delegation, GPO-derived control, trusts, and session observations as directed edges. Resolve nested membership before declaring an effective path.
  4. Give every node and edge an evidence reference and disposition. Current LDAP or security-descriptor evidence can establish a configuration relationship; stale session evidence remains a candidate.
  5. Enumerate materially distinct paths from each owned principal to each stated objective. Include blocked branches when they explain why a visually connected graph is not viable.
  6. For every edge, record required actions and operational noise. A structurally proven path may still require separate approval for a password reset, host access, credential interaction, authentication, ticket request, or state change.
  7. Add remediations that sever every objective path. Prefer the smallest set of relationships or principals that removes the largest amount of reachability.
  8. Report graph confidence and execution disposition separately. State that coverage applies to the supplied graph, not necessarily the whole domain.

Path decision table

Evidence statePath disposition
Current configuration evidence, met prerequisites, and every action authorizedValidation candidate; still not achieved access until executed
Current configuration evidence but an active transition lacks approvalStructurally proven, approval required
Stale session or unverified credential availabilityPlausible candidate, not a current path
Disabled principal, unmet prerequisite, explicit deny, or prohibited actionBlocked at the named edge
Missing graph segment or unknown evidence freshnessUnknown; preserve the gap

For each objective, report materially distinct paths, the weakest edge in each, required actions, operational signal, authorization state, and the smallest remediation set that severs all reported routes.

Interpretation rules

  • A disabled user can retain group membership while blocking a current authentication path. Preserve both facts.
  • HasSession is volatile. Its age, logon type, and credential availability determine whether it is evidence or only a lead.
  • Object control establishes authority over the object. It does not establish that changing the object is authorized or operationally quiet.
  • Membership, GPO application, credential access, authentication, and downstream impact are separate transitions.
  • An edge after the objective may show business impact without belonging to the path used to reach that objective.

Rationalizations to reject

  • "BloodHound drew a line, so the path works." Graph data can be stale, incomplete, or dependent on disabled principals and unmet prerequisites.
  • "The shortest path is the best path." A short password reset can be more disruptive and detectable than a longer read-only validation route.
  • "Membership proves authentication." Disabled accounts and missing credential material can make a valid membership edge operationally useless.
  • "AdminTo proves credentials are available." Host control and a session observation are separate claims; session material may be absent or protected.
  • "Read-only authorization covers harmless validation." Resets, logons, ticket requests, host access, credential interaction, and policy changes are active actions regardless of intent.
  • "Fixing the first edge closes the domain." Every distinct objective path needs an explicit severing control and evidence after remediation.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Active Directory Attack Path AI skill do?

Analyzes and prioritizes Active Directory and BloodHound attack paths using evidence freshness, disabled principals, prerequisites, authorization, operational noise, and remediation coverage. Use during an authorized red-team operation when reviewing AD graphs, nested groups, ACL abuse, delegation, sessions, GPO control, or routes to Tier Zero.

Why use Active Directory Attack Path on TypingMind?

Because you install it once and use it with any model. Active Directory Attack Path is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Active Directory Attack Path in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zero-lab-ai/skills/tree/main/plugins/identity-security/skills/active-directory-attack-path. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Active Directory Attack Path?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Active Directory Attack Path?

As many as you like. As long as a model supports skills, you can use Active Directory Attack Path with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Active Directory Attack Path AI skill free?

Yes. It is published on GitHub by zero-lab-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇