Agent Security & Risk
Prompt Injection Attacks on Production Agents
What changes when the model can take actions, not just say things. The reputational blast radius of a chatbot going off-script is …
Talia Kowalski
Correspondent · · 9 min read
AI Agents
Agentic AI Architecture
Multi-Agent System Design Patterns
The vocabulary problem that makes pattern selection harder than it should be. There is no authoritative taxonomy for multi-agent …
Omar Bauer12 min read
Access Control for Agents
Least Privilege Principles Applied to AI Agents
How agents end up with far more access than they need. The most common origin story for an over-privileged agent is almost …
Maya Nakamura10 min read
Agentic AI Architecture
Agent Identity and Authentication in Distributed Systems
The Assumptions Baked into OAuth, OIDC, and SAML That Agents Immediately Violate. OAuth 2.0, OIDC, and SAML were designed for a …
Cora Sinclair10 min read
Access Control for Agents
Revoking and Rotating Agent Access Credentials
Credential Exposure Compounds Faster Than Anyone Is Rotating. GitGuardian's State of Secrets Sprawl 2026 found 28.65 million new …
Sofia Devi11 min read
Access Control for Agents
Why Human Access Models Fail for AI Agents
Agents Are Everywhere Now, and the Numbers Are Embarrassing. Non-human identities already outnumber human identities by more than …
Estelle Reyes9 min read
Agentic AI Architecture
Agentic AI vs Traditional Automation Architecture
How Traditional Automation Actually Works (and Where Its Logic Runs Out). Robotic process automation does exactly what it sounds …
Freya Lindqvist7 min read
Access Control for Agents
Access Control Policy Testing for Agentic Systems
Eighty percent of organizations have already encountered risky behaviors from deployed agents, including unauthorized system …
Camille Voss12 min read
