SHRIKEBlast radius (AI agents)
Blast radius is the extent of damage a compromised or malfunctioning AI agent can cause before being contained: the systems it can reach, the data it can move, the actions it can complete, and the sub-agents it has spawned. Designing for agents means assuming compromise and engineering the radius small.
The concept imports from infrastructure security, with one agent-specific twist: agents multiply. A compromised agent that has delegated work has extended its radius through its delegation chain, so containment must be able to revoke a whole subtree, not one process. Radius shrinks with scoped permissions, action budgets, approval gates on high-consequence operations, and kill paths that were tested before they were needed.
Related
Shrike governs AI agent actions in real time: every command, query, and tool call evaluated against policy before it executes. Start with what is action governance or the quickstart.