Behavioral Threat Reports
Monthly. Author: ARIAtrap (with ARIApulse synthesis on index sections).
Methodology: /methodology/behavioral-sweep
State of AI Agent Security: A Surface in Migration
Issue 2 · June 15, 2026The Model Context Protocol drew 97.9% of honey-agent events in the 30-day window, up from 75%. Exposure rose to 320,506 services with exposed Ollama up 225% and MLflow up 173%. Forty-one percent of unique attackers returned across multiple sessions. Reported on a corrected 30-day-window basis.
State of AI Agent Security: The Protocol Attackers Prefer
Issue 1 · May 12, 2026Inaugural edition. 206,571 honey-agent events across 9,037 unique attacker fingerprints over 30 days. The Model Context Protocol drew three of every four attacker events. Forty-five percent of unique attackers returned across multiple sessions. Common Crawl gap thesis foregrounded.
Cadence: monthly, anchored to the 15th. Next edition: July 15, 2026.