Wirewalk Instituteof AI
cyb-303 Expert Waitlist

AI for Authorized Penetration Testing and Offensive Security

For professional penetration testers and red team leads who want to use AI to work faster within written authorization, agreed scope and rules of engagement, and to control the new risks AI tools bring into an engagement.

The curriculum is being prepared and reviewed. Enrollment is not open yet.

About this course

Penetration testing is legal only because the system owner has authorized it in writing, for a defined scope and under agreed rules of engagement. AI tools do not change that, but they do create new ways to break it: an autonomous agent that wanders out of scope, client data sent to an unapproved model provider, or a generated exploit run without the review a human tester would apply. This course teaches AI-assisted offensive security entirely inside an authorized engagement.

The first module is the legal and contractual foundation: written authorization from someone with authority over the systems, statements of work, scope definitions down to IP ranges, domains, accounts and cloud tenants, third-party and cloud provider testing policies, rules of engagement including testing windows, prohibited actions, stop conditions and emergency contacts, and frameworks such as TIBER-EU style threat-led testing. Educational, not legal advice. Later modules apply AI to the testing workflow: analyzing open-source reconnaissance output, prioritizing attack surface, assisting web application testing alongside tools such as Burp Suite, reviewing source code and reverse-engineering binaries with Ghidra and LLM assistance, and mapping findings to MITRE ATT&CK. A dedicated module covers autonomous and agentic testing tools: how to constrain them with scope enforcement, action allowlists and human approval, and how to log everything they do. The course closes with AI-assisted reporting that keeps findings accurate and client data protected. It does not teach attacks against systems you are not authorized to test.

What you will be able to do

  • Verify written authorization, scope and rules of engagement before any AI-assisted testing activity
  • Define scope boundaries and stop conditions in a form that both humans and AI tools can enforce
  • Choose AI services for an engagement that meet client data handling and confidentiality requirements
  • Use AI to analyze reconnaissance output and prioritize in-scope attack surface
  • Apply AI assistance to web application, source code and binary analysis while verifying every finding manually
  • Constrain autonomous testing agents with scope enforcement, action allowlists, approvals and full logging
  • Produce accurate, reproducible penetration test reports with AI assistance and no hallucinated findings

Syllabus

6 modules · 18 lessons · about 18 hours

Module 1: Authorization, Scope and Rules of Engagement

The legal and contractual foundation every engagement must have before AI or any tool is used.
4 lessons
  1. Written Authorization: Who Can Grant It and What It Must Say
  2. Defining Scope: Networks, Applications, Accounts and Cloud Tenants
  3. Rules of Engagement: Windows, Prohibited Actions, Stop Conditions and Contacts
  4. Testing Methodologies: PTES, OWASP WSTG, NIST SP 800-115 and Threat-Led Testing

Module 2: AI Tools and Client Data

Bring AI into an engagement without breaching confidentiality.
2 lessons
  1. Choosing Model Providers and Self-Hosted Models for Engagement Data
  2. Data Handling Clauses for AI Use in Statements of Work

Module 3: AI-Assisted Reconnaissance and Web Testing

Speed up analysis of in-scope targets and keep the tester in control.
3 lessons
  1. Analyzing Reconnaissance Output and Prioritizing In-Scope Attack Surface
  2. LLM Assistance in Web Application Testing with Burp Suite
  3. Verifying AI-Suggested Vulnerabilities Before Reporting

Module 4: Code and Binary Analysis

Use AI to read code and binaries faster during authorized assessments.
3 lessons
  1. AI-Assisted Source Code Review in White-Box Tests
  2. Reverse Engineering with Ghidra and LLM Assistance
  3. Mapping Findings and Attack Paths to MITRE ATT&CK

Module 5: Autonomous and Agentic Testing Tools

Keep autonomous tools inside scope and accountable.
3 lessons
  1. What Autonomous Testing Agents Can and Cannot Do
  2. Scope Enforcement, Action Allowlists and Human Approval
  3. Logging, Replay and Evidence of Everything the Agent Did

Module 6: Reporting and Professional Practice

Deliver accurate findings and handle the unexpected professionally.
3 lessons
  1. AI-Assisted Report Writing Without Hallucinated Findings
  2. Handling Out-of-Scope Discoveries and Critical Findings Mid-Engagement
  3. Professional Ethics and Responsible Disclosure

Exam and certificate

The exam unlocks once you have completed every lesson. It draws 25 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 60 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by OWASP, NIST, MITRE, PortSwigger, NSA, OpenAI, Anthropic, or Google. Product and company names are trademarks of their respective owners.

More in Security by AI: AI for Cyber Defense

All 15 courses in this track
cyb-001 Free intro Available

Spotting AI Scams, Deepfakes and AI-Powered Phishing

Learn what generative AI has changed about scams, from cloned voices and deepfake video calls to fluent phishing, and build a short set of verification habits that work no matter how convincing the fake is. Free, about one hour, with a 10-question check at the end.

1 h · 6 lessons Free intro
cyb-101 Basic Waitlist

AI in Cybersecurity: An Introduction

A plain-language introduction to AI in cyber defense: the difference between classic machine learning detection and LLM assistants, where each shows up across the security stack, how attackers are using AI, and how to judge a security AI claim. No coding or security background beyond IT basics is required.

6 h · 15 lessons Join the waitlist
cyb-102 Basic Waitlist

Using AI Assistants Safely in Security Work

Practical rules for using general-purpose and security-specific AI assistants in security work: classifying what can be shared, sanitizing logs and malware samples, verifying output before acting, handling untrusted content that may carry prompt injection, and keeping an auditable record. Ends with a one-page team policy you can adopt.

6 h · 13 lessons Join the waitlist