[tl;dr sec] #329 - AI-powered Honeypots, GitHub Action Canaries, Microsoft’s Agentic Security Scanner
Detecting and deceiving attackers with AI honeypots, detect supply chain attacks with GitHub Action canaries, the latest from Microsoft's new "Autonomous Code Security" team
Read the full articleYou might also wanna read
Agent Security Under Fire: GitHub Exploit, Supply Chain Attack, and Microsoft Foundry Updates
This week highlighted critical security vulnerabilities in agentic AI systems alongside a major infrastructure update from Microsoft. A flaw
New “Agentjacking” Attacks Could Hijack AI Coding Agents
Tenet Security researchers reveal how new “agentjacking” attacks could trick coding agents into executing arbitrary code
Investigating suspicious AI workflows in Microsoft Entra Agent ID: Autonomous agents
Read our primer on how to detect and respond to an autonomous agent escalating privileges and persisting in your Entra ID tenant
Microsoft Pushes Agentic AI Security with New Multi-Model Defense System
A new agentic AI security multi-model defense system built by Microsoft's Autonomous Code Security team helped researchers find 16 new vulne
Security Vulnerabilities in Agentic AI Browsers: Testing Reveals Scam Susceptibility
We Put Agentic AI Browsers to the Test - They Clicked, They Paid, They Failed
guard.io·10mo ago
The new architecture of power: Best infosec long reads 6/27/26
The UK's untrustworthy crime prediction machine, Scattered Spider didn't attack Jaguar Land Rover, A powerful new side channel attack, Trump
metacurity.com·18d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.