Skip to content
Agentic Cyber Kit

Personal blog · security notes and projects

Secure every hop your AI agents make.

Notes and hands-on projects exploring how to make AI agents safer. I focus on how agents connect to AI models, tools, and one another and how to manage their access and keep track of what they do. I build small projects in my own time and share the code and lessons learned.

ABOUT ACK

What is ACK?

ACK stands for Agentic Cyber Kit. It’s a place to share what I’m learning about AI security through practical projects. I publish the code, step-by-step labs, and notes so you can try them yourself.

coverage

What the projects cover

Across the projects I work through the main areas of AI security, from the traffic between agents to the data they handle.

A → LLM

Agent to LLM

  • Virtual keys per agent
  • Prompt guards and redaction
  • Token and budget limits

A → MCP

Agent to tools (MCP)

  • Authenticated tool access
  • Per-identity tool scoping
  • Guardrails on tool calls and responses
  • Audit trail

A → A2A

Agent to agent (A2A)

  • An identity for every agent
  • mTLS
  • Authorization on each hop
  • End-to-end tracing

Across all projects

Prompt injection

how attacks reach an agent through its inputs, and what stops them.

Guardrails

filtering what goes into and comes out of a model.

MCP server trust

checking the tools an agent is allowed to load.

Secrets for agents

short-lived credentials instead of long-lived keys.

Audit and tracing

knowing which agent did what, and why.

Data protection

keeping sensitive data out of prompts and logs.

projects

Latest project

PublishedProject 2

Securing an AI SRE agent on Kubernetes

I let HolmesGPT investigate a Kubernetes incident with read-only access and give the repair to a separate operator agent with its own identity.

Read the project →

notes

Latest notes

All notes →

feedback

Found a mistake, have an idea, or want to talk about agentic security? Open an issue on GitHub or get in touch.