AI Agentic Security & Data Governance Training Malaysia | HRDC Claimable — AITraining2U
Cybersecurity & AI Governance

AI Agentic Security &
Data Governance

Protect your organisation's AI systems from emerging threats. Master cybersecurity fundamentals, AI agent security, vulnerability scanning, and enterprise data governance. Hands-on training with real security tools.

Workshop Dates

Register your interest to be notified when dates are announced.

Dates Coming Soon

Register your interest and be the first to know when we announce workshop dates for this programme.

Register Your Interest

Private Corporate Training

Looking to secure your entire organisation's AI infrastructure?

Exclusive sessions available for groups of 25-35 pax per class. Fully claimable.

5 Core AI Threat Areas. Hands-On.

The AI-specific attack surfaces every security professional must master. Each one is taught with live attack-and-defend exercises.

Prompt Injection

Defending against direct & indirect injection

Prompt Theft

Protecting system prompts & IP

Secret & Credential Exposure

Preventing API key & token leaks

Insecure Tool Use

Hardening agent tool-calling surfaces

Sensitive Data Disclosure

Stopping accidental PII & PDPA leaks

What You'll Build

Practical security projects you will complete during the workshop.

Threat Detection

AI Agent Threat Scanner

Build an automated scanner that identifies vulnerabilities in AI agent configurations, API endpoints, and data flows.

Compliance

OWASP AI Security Audit Tool

Implement OWASP Top 10 for LLM Applications checks against your AI systems with automated reporting.

AI Defence

Prompt Injection Defence

Build multi-layered defences against direct and indirect prompt injection, jailbreaking, and adversarial inputs targeting AI agents.

IP Protection

Prompt Theft Defence

Detect and block attempts to extract proprietary system prompts, custom instructions, and embedded business logic from your AI agents.

Credential Security

AI Secret & Credential Exposure Detection

Scan code, prompts, and agent contexts for leaked API keys, tokens, and credentials. Prevent the most common cause of AI security incidents.

API Security

API Security Gateway

Deploy a security gateway that monitors, rate-limits, and validates all AI API traffic with anomaly detection.

HRDC Training Architecture

A structured, hands-on approach to mastering AI security and data governance.

Day 1: Cybersecurity Foundations & AI Threat Landscape

Understanding the core security mechanics and the AI-specific threat landscape.

Phase 01

Core Theory

  • Cybersecurity Fundamentals: CIA triad, attack surfaces, threat modelling, defence-in-depth strategy. The essential foundation before adding the AI layer.
  • AI-Specific Threat Landscape: Prompt injection, data poisoning, model theft, adversarial attacks, hallucination exploitation. How AI agents create new attack vectors.
  • OWASP Top 10 for LLM Applications: Deep dive into each vulnerability category: prompt injection, insecure output handling, training data poisoning, model denial of service, supply chain vulnerabilities, sensitive information disclosure, insecure plugin design, excessive agency, overreliance, model theft.
  • Malaysian Regulatory Context: PDPA compliance, BNM RMiT for financial services, Cybersecurity Act 2024, industry-specific requirements and how AI intersects with existing regulations.

Hands-On Labs

Prompt Injection Attack & Defence

Run direct and indirect prompt injection attacks against a live AI agent. Build layered defences — input filtering, output validation, and tool-allowlists — and re-test until each attack is blocked.

Prompt Theft & Extraction Testing

Use known prompt-extraction techniques to attempt to leak proprietary system prompts and embedded business logic. Implement counter-measures that protect IP without breaking legitimate use.

AI Secret & Credential Exposure

Scan repositories, prompts, and agent contexts for leaked API keys, tokens, and credentials. Apply rotation, vaulting, and least-privilege patterns to prevent the most common AI security incident.

AI Attack Surface Mapping

Map your AI infrastructure end-to-end. Identify exposed endpoints, misconfigured tool surfaces, weak authentication, and PDPA-relevant data flow risks across the agent lifecycle.

Day 2: AI Agent Security & Data Governance

Securing AI agents, implementing governance, and advanced penetration testing.

Phase 02

Core Theory

  • Securing AI Agents: Authentication, authorisation, sandboxing, output validation, tool-use restrictions. How to prevent AI agents from being weaponised or manipulated.
  • Data Governance Frameworks: Data classification, access control matrices, retention policies, data lineage tracking, right-to-erasure compliance for AI training data.
  • API & Integration Security: Securing AI API endpoints, rate limiting, input validation, output sanitisation, webhook security, and MCP server hardening.
  • Security Architecture for AI Systems: Zero-trust principles applied to AI, network segmentation, secrets management, encrypted communication, and secure model deployment patterns.

Hands-On Labs

AI Agent Penetration Testing

Conduct structured penetration tests against a live AI chatbot: prompt injection attacks, prompt theft attempts, sensitive data extraction, and privilege escalation through tool misuse.

Continuous Vulnerability Scanning

Set up automated, scheduled vulnerability scans across your AI stack — endpoints, agent surfaces, and supporting infrastructure — with alerting for new exposures.

Building Defence Layers

Implement input sanitisation, output filtering, rate limiting, and anomaly detection for an AI agent. Test each layer against known attack patterns and tune thresholds.

Secrets & Credential Hardening

Audit how secrets flow through your AI workflows. Implement rotation, vaulting, and least-privilege access for the credentials AI agents use to call internal systems.

Day 3 (Optional): Enterprise AI Security Operations & Strategy

Phase 03

Specifically designed for corporate consulting engagements. Covers:

  • Security operations design for AI-augmented environments
  • Threat intelligence integration with AI systems
  • Red team / blue team exercises for AI security
  • Building an AI security policy framework
  • Vendor risk assessment for AI tools and platforms
  • Board-level security reporting and risk communication
  • Developing an organisational AI security roadmap

Who Should Attend?

This hands-on intensive is designed for technical professionals responsible for AI security and data governance.

IT Security Teams & CISOs

Security professionals responsible for securing AI deployments and ensuring regulatory compliance.

Software Engineers & DevOps

Developers building AI-powered applications who need to implement security-by-design principles.

Data Protection Officers

Compliance professionals managing data governance, PDPA requirements, and AI data handling policies.

CTOs & Technical Leaders

Decision-makers evaluating AI security risks and building organisational security strategies.

Experience the Workshop

A hands-on, high-energy environment where teams actually build, not just listen.

AITraining2U Workshop Experience Collage

Our People

Learn from Malaysia's top AI security practitioners.

Shah Mijanur Rahman

Shah Mijanur Rahman

Cybersecurity & Agentic Security Expert

Expert in cybersecurity, data pipelines, and AI agent security. Specialist in securing enterprise AI deployments, conducting penetration testing, and implementing data governance frameworks. Optimizes how AI agents retrieve and process internal knowledge securely.

Detailed FAQ

Addressing your technical, logistical, and HRDC inquiries.

This course is designed for IT security teams, CISOs, software engineers, DevOps teams, data protection officers, and technical leaders who need to understand how to secure AI systems and implement data governance. Prior technical experience is expected, but deep cybersecurity expertise is not required.
The course is built around the five highest-impact AI security threat areas: prompt injection (direct and indirect), prompt theft and system-prompt extraction, AI secret and credential exposure, insecure agent tool-use, and sensitive data disclosure. Each is taught with live attack-and-defend exercises, mapped against the OWASP Top 10 for LLM Applications and Malaysian regulatory requirements (PDPA, BNM RMiT, Cybersecurity Act 2024).
Basic IT knowledge is required, but you don't need to be a security specialist. The course starts with cybersecurity fundamentals before layering on AI-specific security concepts. We cover everything from the CIA triad to advanced AI agent penetration testing.
Yes. AITraining2U is a registered HRD Corp training provider. This course is 100% HRDC claimable for Malaysian companies. We handle all documentation and submission.
Traditional cybersecurity courses don't cover AI-specific threats like prompt injection, model theft, or adversarial attacks on AI agents. This course bridges the gap by teaching cybersecurity fundamentals alongside the unique security challenges of deploying AI agents, LLMs, and automated AI systems in production.

Course Fee

Transparent pricing for your AI security transformation journey.

Self-Funded (non-HRDC)

Kickstart your AI Security journey

RM 3,200 +8% SST
  • 2 full days of in-person intensive training
  • Complete programme materials, tools and templates
  • Certificate of Completion
  • 3-month post-training WhatsApp group support
  • Admission to wider AI Learning Community
Sign Up
Most Popular

HRDC-Claimable

Upskill with your company's HRDC grant

RM 3,500 +8% SST
  • 2 full days of in-person intensive training
  • Complete programme materials, tools and templates
  • Certificate of Completion
  • 3-month post-training WhatsApp group support
  • Admission to wider AI Learning Community
Sign Up
HRDC Claimable and Registered Provider

About AITraining2U

AITraining2U was established by professionals to close the divide between academic theory, business and practical industry demands. Our mission is to ensure that AI education translates directly into measurable, real-world results. Since 2025, we have upskilled over 1,200 professionals across Malaysia in AI, Business Transformation, Agentic Automation, and Vibe Coding.

Driven by a core philosophy of "100%-focus on success" our expert faculty delivers highly interactive, hands-on learning experiences focused entirely on implementation. We don't just teach prompt engineering; we teach you how to architect robust, autonomous systems.

Whether through bespoke corporate masterclasses or intensive public bootcamps, we actively partner with enterprise leaders, technical specialists, and government bodies to accelerate their digital transformation journey and build confident, AI-native organizations.

Secure Your AI Systems Today

Register Interest