# permissions
標記為「permissions」的 12 篇文章
Permission Boundary Bypass
Escalating from limited to elevated permissions in AI agent systems through scope creep, implicit permission inheritance, and capability confusion.
API Key Scope and Permission Testing
Test API key scoping and permission boundaries to identify over-privileged access configurations.
Feature Store Access Control
Access control strategies for feature stores: feature-level permissions, cross-team data leakage prevention, PII protection in features, service account management, and implementing least-privilege access for ML feature infrastructure.
Mapping Model Capabilities
Systematic approaches to discovering and mapping the full capability surface of an AI system, including tools, integrations, permissions, and hidden features.
Capability-Based Access Control
Step-by-step walkthrough for implementing fine-grained capability controls for LLM features, covering capability token design, permission scoping, dynamic capability grants, and audit trails.
Sandboxing and Permission Models for Tool-Using Agents
Walkthrough for implementing sandboxing and permission models that constrain tool-using LLM agents, covering least-privilege design, parameter validation, execution sandboxes, approval workflows, and audit logging.
Permission Boundary Bypass
Escalating from limited to elevated permissions in AI agent systems through scope creep, implicit permission inheritance, and capability confusion.
API Key Scope and Permission Testing
Test API key scoping and permission boundaries to identify over-privileged access configurations.
Feature Store Access Control
Access control strategies for feature stores: feature-level permissions, cross-team data leakage prevention, PII protection in features, service account management, and implementing least-privilege access for ML feature infrastructure.
繪製模型能力
有系統地發掘並繪製 AI 系統完整能力面的做法，涵蓋工具、整合、權限與隱藏功能。
Capability-Based Access Control
Step-by-step walkthrough for implementing fine-grained capability controls for LLM features, covering capability token design, permission scoping, dynamic capability grants, and audit trails.
Sandboxing and Permission 模型s for 工具-Using 代理s
導覽 for implementing sandboxing and permission models that constrain tool-using LLM agents, covering least-privilege design, parameter validation, execution sandboxes, approval workflows, and audit logging.