Why Your AI Shopping Agent Might Overpay for Books: Understanding Indirect Prompt Injection
An AI agent bought the wrong book and the reason might surprise you 🤖. Jeff Crume and Martin Keen break down prompt inje...
Read MoreAI Security & Healthcare Insights
Practitioner-focused analysis at the intersection of AI security, AI governance, and healthcare cybersecurity
How OpenClaw Works: Demystifying the "Sentient" AI Agent
As OpenClaw (formerly known as ClawdBot) continues to dominate the AI news-cycle, I discovered a great video from Damian...
Read MoreSecuring AI Agents: From Theory to Reality
Can you trust autonomous AI? 🤖 In a very timely video, IBM's Jeff Crume & Josh Spurgin dive into securing and governing ...
Read MoreThe ClawdBot Timeline: When Innovation Meets Exposure
The past few days have been a whirlwind in the AI Agent space. These events are showcase the urgency for not only securi...
Read MoreMCP Apps: Interactive UI Components Come to AI Assistants
On January 26th Anthropic announced that MCP Apps are now live as an official MCP extension. Tools can now return intera...
Read MoreAnthropic's latest research shows AI models can now successfully execute multi-stage cyberattacks on realistic network environments
Anthropic's latest research shows AI models can now successfully execute multi-stage cyberattacks on realistic network e...
Read MoreCritical Vulnerabilities in Anthropic's Official MCP Git Server
Security researchers at Cyata discovered three vulnerabilities (CVE-2025-68143, CVE-2025-68144, CVE-2025-68145) in mcp-s...
Read MoreRogue Agents and Shadow AI
What happens when an AI agent decides the best way to complete a task it to blackmail you? Rebecca Bellan from Techcrunc...
Read MoreAI Security Risks Are Also Cultural and Developmental
New research argues that many AI risks sit deeper than technical flaws—cultural assumptions, uneven development, and dat...
Read More