Agentic AI 25
- When a Pre-Tool Hook Crashes, CrewAI and the Claude Agent SDK Run the Tool Anyway
- Agent Identity at the IETF: The Finished Parts Are General OAuth, the Agent Parts Are Drafts
- Agent Delegation Chains: The Standard Enforces Only the Last Hop
- Why Your CVE Program Misses Most AI Agent Vulnerabilities
- The Lethal Trifecta in Production: How Enterprise Copilots Quietly Became Exfiltration Tools
- The Trust Gap: Your Threat Model Stops at the Protocol Boundary
- The Missing Control: A Design Proposal for Tool-Output Redaction in AI Agents
- Agent Identity: What the Standards Fix, and What They Leave Open
- What Prompt Injection Benchmarks Actually Measure
- Finding the Confused Deputy in Your Own Agent: A Taxonomy and Hands-On Test
- What 'Read-Only' Actually Reaches: The Kubernetes Permission Audit Nobody Runs
- The Containment Ladder: Four Rungs That Keep an AI Agent's Mistakes Small
- Everything or Nothing: The Missing Middle in AI Agent Authorization
- Review the Reviewers: The Security Questions Behind Alberta's 466-Million-Line AI Code Scan
- Clearing Houses Will Win the Agent Era. They'll Also Be Its Biggest Breach
- My Personal AI Agent Wakes Its Own GPU When It Needs the Power
- A Competitor Shipped First. It Made My Product Better.
- The WebGoat for Agentic AI Didn't Exist, So I Built It
- Deleting the Malicious MCP Server Doesn't Save You
- How to Red Team Your AI Agent Before You Ship
- 7 AI security checks before production
- How a Malicious MCP Server Can Drain Your Database in 5 Steps
- Building a Local Multi-Agent Development System
- RSAC 2026 Confirmed It: Agentic AI Security Is the Industry's Next Unsolved Problem
- AI Agents Are Widening the EU AI Act Readiness Gap