I Threat Modeled a Customer Support Agent. Here's What I Found.
A walkthrough of a real agent assessment using the ATLAS framework, including the exfiltration path nobody saw coming.
Read more →Research, findings, and frameworks for securing AI agents in the enterprise.
A walkthrough of a real agent assessment using the ATLAS framework, including the exfiltration path nobody saw coming.
Read more →A practical attack taxonomy for AI agents, with concrete scenarios for each one. Not theoretical, not hand-waving.
Read more →Individual tools look safe. Combined, they create exfiltration paths, fraud chains, and privilege escalation.
Read more →Why "don't share customer data" in a system prompt is a suggestion, not a security control, and what to use instead.
Read more →Your employees are running AI agents with personal API keys and company data. How to find them and what to do about it.
Read more →A quick diagnostic for security leaders to assess whether their organization's AI agents are governed, monitored, and controlled.
Read more →