NIST
NIST AI Risk Management Framework
A practical foundation for governing and managing AI risk across the system lifecycle.
GovernanceRisk
Open resource Knowledge base / Field references
Resources for building AI that can be trusted.
A curated collection of governance frameworks, threat models and open-source tools for secure enterprise AI.
Governance & frameworks
Standards and operational guidance for accountable AI.
ENISA
Multilayer Cybersecurity Framework for AI
European guidance for securing AI systems, operations and processes through layered controls.
EUSecurity
Open resource NIST AIRC
AI Resource Center
Operational resources for testing, evaluation, verification and validation of trustworthy AI.
TEVVPlaybooks
Open resource Threat intelligence
Models for understanding how AI systems fail and how adversaries exploit them.
OWASP GenAI
Top 10 for LLM Applications 2026
The current community-driven reference for critical risks in generative AI applications.
LLMSecurity
Open resource OWASP GenAI
Top 10 for Agentic Applications 2026
A focused risk model for autonomous systems that plan, use tools and act across workflows.
AgentsThreats
Open resource MITRE
ATLAS
A knowledge base of adversary tactics and techniques targeting machine-learning systems.
Adversarial MLTTPs
Open resource Open-source tools
Projects that help teams test, constrain and harden AI systems.
NVIDIA
NeMo Guardrails
An open-source toolkit for programmable conversational and topical guardrails.
PythonGuardrails
Open resource Trusted AI
Adversarial Robustness Toolbox
Tools for evaluating and defending against evasion, poisoning, extraction and inference attacks.
ML SecurityRed Team
Open resource Microsoft
PyRIT
An automation framework for identifying risks in generative AI systems through adversarial testing.
GenAIRed Team
Open resource GITHUB / RLEALZ
Explore Ricardo Leal's open-source work
Repositories spanning AI agents, cybersecurity, Web3 and applied product engineering.
LEAL STRATEGY / ADVISORY
Need a framework adapted to your organisation?
Turn public guidance into controls, architecture and an operating model aligned with your organisation's risk profile.