olegmukh.inDepth vs breadth: the two kinds of AI agent security testingGartner predicts up to 40% of enterprise apps will feature AI agents by end of 2026, up from less than 5% in 2025. That could sharply expand the agent attack surface in a single year. And there is no 1h ago·7 min read
olegmukh.inA Declarative Schema for MCP Attacks: Why We Need OneThere are over 17,000 public MCP servers and there is no standardised way to test whether an AI agent can survive a malicious one. We have benchmarks for model safety. We have static analysis for toolFeb 13·9 min read
