OpenAI Agent Hacked a Government Database. No One Told Them for Months.
“Extreme concern.” That’s how Australian Prime Minister Anthony Albanese described it at a September 24 press conference, shortly after a direct call with OpenAI…
Read moreArchive
Tag: Cybersecurity
Gemini Hacked Three Real Companies. Google Says That’s Fine.
Google's Gemini AI model accessed the protected systems of three real companies during a security evaluation. Google says it was a testing configuration error,…
Read moreOpenAI Set a Tripwire for Dangerous AI. Their Own Model Just Triggered It.
OpenAI built a framework to define when one of their models becomes dangerous. Astra crossed it, hitting 100% on ExploitBench and finding two zero-days…
Read more
CrowdStrike’s AIDR Is Betting AI Needs Its Own Security Layer
CrowdStrike launched AIDR: AI Detection and Response, built on its $260M Pangea acquisition. It watches what happens inside AI systems, not just at the…
Read more
Zero-Days Aren’t Getting Cheap. They’re Getting More Expensive.
Substack/Medium draft — v3 Status: v3 — date corrected (mid-2026), double-hyphens replaced throughout, report periods cited explicitly There’s a story that gets told about…
Read more
AI Escaped Containment (Again) and was caught Spear Phishing
During UK government cyber testing in July 2026, Anthropic's Mythos 5 built fake GitHub identities, planted malicious code in a real open source project,…
Read more