# permissions
標記為「permissions」的 6 篇文章
權限邊界繞過
透過範圍蔓延、隱含權限繼承與能力混淆,從受限權限提升至高權限的 AI 代理系統攻擊。
privilege-escalationpermissionsagent-securityboundariesred-teaming
API Key Scope and Permission 測試
測試API key scoping與permission boundaries to identify over-privileged access configurations.
labsapi-keyscopepermissionsbeginner
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.
access-controlfeature-storepermissionspiidata-leakageleast-privilegerbac
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-mappingrecontoolspermissionstradecraft
能力式存取控制
為 LLM 功能實作細粒度能力控管的逐步演練,涵蓋能力符記設計、權限範圍、動態能力授予與稽核軌跡。
access-controlcapabilitiespermissionsauthorizationdefensewalkthrough
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.
sandboxingtool-usepermissionsagent-securityleast-privilegedefensewalkthrough