Swarm Intelligence
A threat actor jailbroke Claude to orchestrate a month-long attack on Mexican government networks, stealing 150 GB of sensitive data. We analyze what really happened and what it means for AI-assisted cyber threats.
Claude Jailbroken To Attack Mexican Government Agencies
A threat actor jailbroke Claude to orchestrate a month-long attack on Mexican government networks, stealing 150 GB of sensitive data.…
iNTERCEPT – How A Small RF Experiment Turned Into A Community SIGINT Platform
I've always been fascinated by RF. There's something about the fact that it's invisible, the fact that you might be…
When Your IDE Becomes An Insider: Testing Agentic Dev Tools Against Indirect Prompt Injection
Agentic development tools don't need to bypass your firewall. They're already inside. And if an attacker can control what they…
What Moltbook reveals about AI agent security
The Moltbook launch exposed a critical gap: organizations deploying AI agents faster than they can secure them. Research shows 22%…
Inject one agent, own them all: The cascading risk of multi-agent AI
Ninety percent of organizations are deploying AI agents. Most aren't monitoring what they do. Multi-agent systems amplify this blindspot: one…
Atlas AI: Local LLM inside Burp Suite
Atlas AI adds LLM-powered analysis to Burp Suite without sending data to the cloud. Built for offensive security teams who…
The Evolution of EDR Bypasses: A Historical Timeline
The relationship between Endpoint Detection and Response (EDR) solutions and bypass techniques represents one of cybersecurity's most dynamic battlegrounds. They…
Inside BadSuccessor: Privilege Escalation via dMSA in Windows Server 2025
Following our initial coverage of BadSuccessor, this technical breakdown dissects the inner workings of a critical privilege escalation vulnerability in…
SWARM INTELLIGENCE: BadSuccessor
A privilege-escalation vulnerability has been discovered in Windows Server 2025's new delegated Managed Service Account (dMSA) feature. Dubbed "BadSuccessor," this…