Correlic Blog — Kernel-Level Security Observability for AI Coding Agents

Write

Your AI Agent Got Poisoned Through a Tool Description. Here's Why Only the Kernel Saw It Coming.
MCP tool poisoning is the attack you can't see in your UI. We built the defense you can see in your kernel. In Part 3, I covered how we taught Correlic's AI investigation layer to analyze security inc
Apr 20, 202613 min read3
I Built an AI System to Investigate AI Agents. Here's What I Learned About Making It Not Lie.
*From raw incident timelines to confident, evidence-grounded analysis — the engineering decisions behind Correlic's AI investigation layer.* In [Part 2](https://correlic.hashnode.dev/your-ai-agent-mad
Apr 11, 202614 min read7
C
Correlic Blog — Kernel-Level Security Observability for AI Coding Agents
5 posts
Kernel-level security observability for AI coding agents. Follow our journey building Correlic — from eBPF syscall tracing to intelligent threat detection. Deep dives into agent security, system call analysis, and why every AI action on your machine deserves a watchdog.
[Part 2] Building Correlic: Your AI Agent Made 70 System Calls Per Second. Here's How I Taught My System Which Ones Matter.
Four failed attempts at teaching a machine what matters — and the baseline system that finally got it right.
Apr 9, 202615 min read4
[Part 1] Building Correlic: Capturing Every Action Your AI Agent Tries to Hide
Four failed attempts, one kernel breakthrough, and the real cost of making AI agents transparent
Apr 4, 202619 min read16
Do You Actually Know What Your AI Coding Agent Did in the Last Hour?
~/.ssh/id_ed25519 was read 47 seconds ago. Not by you.
Mar 31, 20267 min read16

Command Palette

Latest articles