AI Coding Agent Horror Stories: Security Risks Explained | Docker
Explore real AI coding agent security failures, from database wipes to secrets leakage, and learn how Docker Sandboxes reduce the blast radius.
New OpenClaw AI agent found unsafe for use
kaspersky.comWe explore whether OpenClaw can be safely installed and configured, and the risks involved in running this experiment.
Introducing GREMLIN, My AI-Powered Assistant
Meet GREMLIN, my always-on AI assistant built with OpenClaw that books flights, makes reservations, handles scheduling, and sends morning briefings.
I built a personal AI agent and then killed it
Yeah, that title’s kind of sensationalist. “You won’t believe what happened next!” Since I’m a human and we pack-bond with and anthropomorphize everything, I actually …
The OpenClaw Warning: From Viral Sensation to Security Nightmare
OpenClaw promised to be the personal AI assistant that actually does things. It orders your groceries, triages your inbox, negotiates y...
The Curious Case of the Triton Malware Fork
Today, a weird malware distribution campaign targeting users of omg.lol and Triton, an open-source macOS client of omg.lol, was found. The attack leverages the trust of GitHub, creating a malicious fork where the download link has been replaced with malware hidden in presented .zip file.
My Malware Story Gets Stolen; Yet Another Argument for the IndieWeb
A few days after writing about a weird malware campaign, I discovered that half a dozen cybersecurity news outlets had picked up the story. They now outrank me on Google. A metacommentary on the state of internet journalism, attribution, and what it says that a netsec industry has to rely on amateurs to break stories.
The vulnerability landscape in Q1 2026
This report provides statistical data on published vulnerabilities and exploits we researched during Q1 2026. It also includes summary data on the use of C2 frameworks in APT attacks.