Wirewalk Instituteof AI
sec-220 Intermediate Waitlist

Securing AI Agents, Tools and MCP Integrations

For security engineers, platform teams and developers who deploy AI agents and need to control what those agents can access, call and change, including through MCP servers.

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

About this course

An agent is software that decides at run time which tools to call with which arguments, so the security question shifts from what the user can do to what the agent can be talked into doing. This course treats agents as identities with privileges. You start with agent anatomy, the OWASP Top 10 for Agentic Applications (ASI01 to ASI10, released December 2025) and the Five Eyes joint guidance Careful Adoption of Agentic AI Services (May 2026). You then design agent identity and authorization: workload identities, on-behalf-of access with scoped OAuth tokens, user-scoped authorization enforced outside the model, and least agency through allowlists, parameter constraints and budgets.

A full module covers the Model Context Protocol as of the 2026-07-28 specification: its trust model, OAuth-based authorization and audience-bound tokens, confused-deputy risks, tool poisoning and rug pulls, and how to vet, pin and host servers. You will design execution sandboxes (containers, gVisor, microVMs) with egress and secret controls, secure inter-agent communication including A2A, contain cascading failures and rogue agents, and lock down coding agents in developer environments. The course ends with audit-grade tracing, kill switches and a pre-production checklist. Prompt injection mechanics are covered in depth in sec-210. The Wirewalk Institute certificate attests to completion and assessment of this course; it is not endorsed by OWASP, MITRE, NIST or any vendor named here.

What you will be able to do

  • Explain each risk in the OWASP Top 10 for Agentic Applications and map it to an agent architecture
  • Design agent identities and on-behalf-of authorization so access is enforced outside the model
  • Apply least agency through tool allowlists, parameter constraints, budgets and approval steps
  • Secure MCP clients and servers against confused-deputy, tool poisoning and server impersonation risks
  • Specify sandboxes for agent code execution with filesystem, network egress and secret controls
  • Contain multi-agent failures with authenticated messaging, circuit breakers and kill switches
  • Run a pre-production security review of an agent deployment using traces and a checklist

Syllabus

6 modules · 19 lessons · about 14 hours

Module 1: Agent Architectures and Their Risks

How agents work and the current reference lists and guidance for their risks.
3 lessons
  1. Anatomy of an Agent: Planner, Tools, Memory and Runtime
  2. The OWASP Top 10 for Agentic Applications (ASI01 to ASI10)
  3. Five Eyes Guidance: Careful Adoption of Agentic AI Services

Module 2: Identity and Authorization for Agents

Giving agents identities and limiting what each identity can do.
3 lessons
  1. Agent Identities: Service Accounts, Workload Identity and Delegation
  2. On-Behalf-Of Access: OAuth Scopes, Token Exchange and User-Scoped Authorization
  3. Least Agency: Tool Allowlists, Parameter Constraints and Budgets

Module 3: Securing the Model Context Protocol

The MCP trust model and the controls clients, servers and operators need.
4 lessons
  1. MCP Architecture and Trust Model in the 2026-07-28 Specification
  2. MCP Authorization: OAuth, Audience-Bound Tokens and the Confused Deputy
  3. Tool Poisoning, Rug Pulls and Server Impersonation
  4. Vetting, Pinning and Hosting MCP Servers

Module 4: Execution Sandboxes and Runtime Controls

Containing what agents execute and touch.
3 lessons
  1. Sandboxing Code Execution: Containers, gVisor and MicroVMs
  2. Network Egress, Filesystem Scope and Secrets in Agent Runtimes
  3. Approval Steps People Will Not Rubber-Stamp

Module 5: Multi-Agent and Developer Agents

Inter-agent trust, cascading failures and coding agents.
3 lessons
  1. Inter-Agent Communication: A2A, Message Authenticity and Trust Boundaries
  2. Cascading Failures and Rogue Agents (ASI08 and ASI10)
  3. Coding Agents in Developer Environments: Repositories, CI and Credentials

Module 6: Operating Agents Safely

Observability, emergency controls and the review before go-live.
3 lessons
  1. Tracing and Logging Agent Actions for Audit
  2. Kill Switches, Rate Limits and Rollback
  3. Agent Deployment Security Review: A Pre-Production Checklist

Exam and certificate

The exam unlocks once you have completed every lesson. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 45 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, Model Context Protocol, Agent2Agent (A2A), CISA, or NSA. Product and company names are trademarks of their respective owners.

More in AI Security: Securing AI Systems

All 13 courses in this track
sec-001 Free intro Available

Using AI Safely at Work: The Essentials

Follow one fictional US distributor through four everyday AI mistakes (a guarantor's credit file uploaded to a personal account, a customer letter promising a fee waiver that does not exist, a vendor email with hidden instructions for the assistant, and a note-taker that sent a customer the internal margin floor) and practice the decisions that prevent or contain each one in three short Decision Labs.

1 h · 7 lessons Free intro
sec-101 Basic Available

Using AI Safely: Data Handling for Every Employee

A plain-language course on handling data safely with AI tools: what happens to what you type or upload, how to classify before you paste, how connected apps and agents change the picture, and how to report a mistake quickly.

6 h · 15 lessons See price at checkout
sec-201 Intermediate Available

AI Security Fundamentals: The OWASP Top 10 for LLMs

A practitioner course on securing applications that use large language models, organized around the 2026 OWASP Top 10 for LLM Applications. Every risk comes with a hypothetical scenario, the root cause, and concrete defenses in code and configuration.

14 h · 18 lessons See price at checkout