https://mpklu.github.io/tags/defense/Recent content in Defense on AI Coding BlogHugoen-usSun, 11 Oct 2026 20:40:00 -0400https://mpklu.github.io/posts/agentic-threat-4-fighting-agents-with-agents/Sun, 11 Oct 2026 20:40:00 -0400https://mpklu.github.io/posts/agentic-threat-4-fighting-agents-with-agents/<p><em>Defending a computer has always meant building walls and waiting. The attacker moves, you react, and the distance between those two things is measured in human hours — because somewhere in the middle a person has to read an alert and decide whether it matters.</em></p> <p><em>That gap is now the entire game. Attacks arrive in seconds. A careful investigation still takes someone an afternoon.</em></p> <p><em>So: if the attackers get agents, can we have some too? The answer turns out to be yes, and cheaply — but the more useful question is who should be holding them. Because almost everything written about this points the work at the people least able to do it.</em></p>https://mpklu.github.io/posts/agentic-threat-3-worms-made-of-sentences/Sun, 11 Oct 2026 20:30:00 -0400https://mpklu.github.io/posts/agentic-threat-3-worms-made-of-sentences/<p><em>For forty years, malware was code. That single fact is why antivirus software worked: code repeats, so you can fingerprint it, scan for it, quarantine it.</em></p> <p><em>What happens when the thing reading your files is a reasoner, and the payload is a paragraph of ordinary English? The research is already done. The answer is a worm with no code in it at all.</em></p> <hr> <p><em>The Agentic Threat Surface — a five-part series.</em></p>