---
title: "Oleg Mukhin (@olegm) | Hashnode"
description: "Oleg Mukhin (@olegm) writes on Hashnode. Read their latest articles and follow their work."
url: "https://hashnode.com/@olegm"
---

@olegm

# Oleg Mukhin

@olegm · Joined January 2026

### [40 Threat Scenarios for MCP, A2A and AG-UI](https://olegm.hashnode.dev/40-threat-scenarios-for-mcp-a2a-and-ag-ui?utm_source=hashnode&utm_medium=feed)

A browsable threat library of 40 structured attack scenarios targeting MCP, A2A and AG-UI agent protocols, mapped to MITRE ATT&CK, ATLAS and OWASP.

5 min read · [olegm.hashnode.dev](https://olegm.hashnode.dev/40-threat-scenarios-for-mcp-a2a-and-ag-ui?utm_source=hashnode&utm_medium=feed)

[Mar 20](https://hashnode.com/posts/40-threat-scenarios-for-mcp-a2a-and-ag-ui/69bd02e4b238fd45a380de43)

### [Depth vs breadth: the two kinds of AI agent security testing](https://olegm.hashnode.dev/depth-vs-breadth-the-two-kinds-of-ai-agent-security-testing?utm_source=hashnode&utm_medium=feed)

Most agent security tooling focuses on finding new vulnerabilities. But who's checking whether last month's prompt injection still works after a model

7 min read · [olegm.hashnode.dev](https://olegm.hashnode.dev/depth-vs-breadth-the-two-kinds-of-ai-agent-security-testing?utm_source=hashnode&utm_medium=feed)

[Mar 12](https://hashnode.com/posts/depth-vs-breadth-the-two-kinds-of-ai-agent-security-testing/69b2165c6c896b0519d691a0)

### [A Declarative Schema for MCP Attacks: Why We Need One](https://olegm.hashnode.dev/adversarial-mcp-schema?utm_source=hashnode&utm_medium=feed)

Mapping the OWASP MCP Top 10 to Adversarial YAML Definitions

9 min read · [olegm.hashnode.dev](https://olegm.hashnode.dev/adversarial-mcp-schema?utm_source=hashnode&utm_medium=feed)

[Feb 13](https://hashnode.com/posts/adversarial-mcp-schema/698ed303070ffe024e334a7c)