中文 EN

Scan Report

Scan New Files

This report was generated in Chinese. Some content may be in Chinese.
✓ Trusted — Risk Score 0/100
Last scan:5 hr ago Rescan
0 /100
agent-memory-architecture
Implement the 5-file agent memory architecture for durable continuity across sessions
纯文档类AI技能，无任何可执行代码，仅提供AI代理记忆系统设计的指导规范，包含积极的安全最佳实践。
Skill Nameagent-memory-architecture
Duration26.2s
Enginepi
ClawHub Agent Memory Architecture v98.0.1 by samledger67-dotcom
📥 201 📦 2
ClawHub Verdict Suspicious llm_suspiciousprompt_injection_instructions
✓
Safe to install
无需任何限制，该技能可直接使用。
ResourceDeclaredInferredStatusEvidence
Filesystem READ READ ✓ Aligned SKILL.md - 创建配置文件模板

File Tree

3 files · 41.1 KB · 1163 lines
Markdown 3f · 1163L
├─ ▾ 📁 references
│ ├─ 📝 memory-templates.md Markdown 183L · 3.2 KB
│ └─ 📝 typing-guide.md Markdown 136L · 4.4 KB
└─ 📝 SKILL.md Markdown 844L · 33.5 KB

Security Positives

✓ 包含提示注入防御规范（Summarize don't parrot原则）
✓ 定义了MEMORY.md加载边界，防止数据泄露到群聊
✓ 强调只读默认原则（Read-only is the standard）
✓ 包含Sacred Files概念，禁止外泄SOUL.md和MEMORY.md
✓ 文档清晰阐述了安全边界和操作规范