Safety, Security, and Privacy (Value)
- Entity ID:
ent-20260423-b002c1000002 - Type:
decision - Scope:
private - Status:
active
Description
Second motivating value. Protects humans, code, data, and infrastructure from harm even when the user is inattentive. Distinct from Human Decision Authority: authority is the human's power to choose; safety is the system's obligation to protect when that power lapses. The auto-mode threat model explicitly targets four risk categories: overeager behavior, honest mistakes, prompt injection, and model misalignment. Motivates defense in depth, deny-first, reversibility-weighted assessment, externalized policy, and isolated subagent boundaries.
Key claims
- none yet
Relations
- Safety, Security, and Privacy (Value) --[motivates]--> Defense in Depth with Layered Mechanisms (Principle)
- Safety, Security, and Privacy (Value) --[motivates]--> Deny-First with Human Escalation (Principle)
- Safety, Security, and Privacy (Value) --[motivates]--> Reversibility-Weighted Risk Assessment (Principle)
- Safety, Security, and Privacy (Value) --[motivates]--> Isolated Subagent Boundaries (Principle)