← AI Agents AI Agents
Browse AI Agents
Topic Hub

Security & Governance

OWASP Top 10 for agentic AI, prompt injection defense, RBAC, EU AI Act compliance, red teaming, and governance patterns.

OWASP Top 10 for Agentic AI Applications Preventing Agent Goal Hijacking (OWASP ASI01) Tool Misuse and Recursive Loop Budgets (OWASP ASI02) Agent Identity and Privilege Abuse (OWASP ASI03) MCP Supply Chain Compromise (OWASP ASI04) Sandboxing Unexpected Code Execution (OWASP ASI05) Red Teaming AI Agent Workflows: Simulating Adversarial Attacks System Prompt Leakage: Detection and Defense Governance-in-the-Loop (GITL): Beyond HITL EU AI Act Compliance for Agentic Systems Data Residency and Context Governance for AI Agents RBAC for MCP Tools with Entra ID Cross-Tenant Data Isolation in Multi-Tenant Agents Model Collapse and Poisoned MCP Ecosystems DORA Regulations for Financial AI Agents Automation Bias and HITL Complacency in AI Agents GITL vs HITL: Governance in the Loop vs Human in the Loop Agents