Behavior Watch

Anomaly detection for AI agent behavior. Monitors tool call patterns, file access sequences, and command history to flag unusual activity — first-seen patterns, frequency spikes, scope creep, and suspicious sequences. Ported from Flare's cloud audit log anomaly detection engine. Trigger phrases: "watch my agent", "behavior audit", "what has the agent been doing", "session activity report", "anomaly check", "agent activity".

ArielSmoliar Updated
safe-agent - Security skills that make AI agents safe to run

File contents

ArielSmoliar/safe-agent commit 9b55a872da

Frequently asked questions

npx get-skill add arielsmoliar/behavior-watch