Definition
The blast radius is the plausible scope of damage, exposure, or irreversible change if a component, credential, or action fails or is compromised. It can be measured across users, tenants, records, money, systems, environments, geography, time, or downstream dependencies.
The phrase comes from the physical area affected by an explosion and is now common in security and reliability engineering. In agent systems, the useful unit is the authority available at the moment of failure. A modest model error paired with production credentials and broad network access can have a larger blast radius than a severe reasoning failure trapped in a disposable, offline sandbox.
Reduce reach before improving prediction
Risk combines likelihood and consequence. Model evaluation works mainly on likelihood. Least privilege, tenant isolation, transaction limits, canaries, staged rollout, reversible operations, human approval, and fast credential revocation reduce consequence. These controls remain valuable even when failure prediction is uncertain.
Distinguish the theoretical maximum allowed by credentials from the effective radius limited by runtime controls, rate limits, monitoring, and recovery. Test whether those controls work under the same compromise you are assuming.
Distinguish it from nearby terms
Attack surface describes ways a system can be reached or exploited. Blast radius describes how far harm can spread after failure. Blast containment is the set of boundaries that restrict that spread. Rollback can reduce duration and persistence but may not undo disclosure or an external irreversible action.
Check your understanding
An agent can delete one temporary table per run, or it can use an administrator credential across every production database. The model and task are identical. Which deployment permits more autonomy? The first has a smaller, more recoverable blast radius and a clearer verification boundary.