📰 Dev.to · Will Velida

Preventing OWASP ASI10 Rogue Agents in a .NET AI agent with behavioural constraints, kill switches, audit logging, immutable tools, and defence in depth.

Preventing OWASP ASI09 Human-Agent Trust Exploitation in a .NET AI agent with medical disclaimers, tool-grounded responses, trust calibration, and confidence in

Preventing OWASP ASI08 Cascading Failures in a .NET AI agent with resilience handlers, structured error responses, caching, and distributed tracing.

Preventing OWASP ASI07 Insecure Inter-Agent Communication in a .NET AI agent with mutual authentication, signed messages, anti-replay, typed contracts, and prot

Preventing OWASP ASI06 Memory and Context Poisoning in a .NET AI agent with session isolation, content validation, cache TTLs, and immutable configuration.

Preventing OWASP ASI05 Unexpected Code Execution in a .NET AI agent with input validation, non-root containers, static tool registration, and runtime monitoring

Preventing OWASP ASI04 Agentic Supply Chain Vulnerabilities in a .NET AI agent with SBOMs, dependency pinning, kill switches, and zero-trust architecture.

Preventing OWASP ASI03 Identity and Privilege Abuse in a .NET AI agent with Entra Agent ID, RBAC, federated credentials, and per-action authorization.

Implementing OWASP ASI02 mitigations against Tool Misuse and Exploitation in a .NET 10 AI agent built with the Microsoft Agent Framework.

My side project (Biotrackr) now has an agent! It's essentially a chat agent that interacts with my...

A practical walkthrough of the OWASP Agentic Top 10, implemented in a real .NET 10 AI agent built with the Microsoft Agent Framework.

Using the Microsoft Agent Framework, we can build agents that interact with our data via chat...

Introduction: The Identity Problem with AI Agents AI agents are moving beyond simple...

Chat history and memory allow agents to maintain context across conversations and remember user...

Almost a year ago, I wrote a blog post on how you could use GitHub Models with Semantic Kernel...