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. Watch an agent get refused in the playground, where every tool call is scanned for real, or read what is action governance.