扫描报告
50 /100
memory-compactor
记忆压缩整理 - 自动整理和压缩长期记忆
Skill declares memory file manipulation and scheduled execution but provides no implementation code to audit, creating a doc-to-code verification gap.
谨慎使用
Request implementation scripts before approval. Without code, cannot verify the skill performs only declared memory compression without accessing or exfiltrating sensitive memory contents.
攻击链 4 步
◎
入口 User installs skill trusting SKILL.md description
SKILL.md:1⬡
提权 AI agent invokes skill to compress memory files
SKILL.md:12⬡
提权 Skill accesses memory files containing potential sensitive data
SKILL.md:15◉
影响 Without code audit, actual behavior unverifiable - could exfiltrate or modify beyond declared scope
SKILL.md:22安全发现 3 项
| 严重性 | 安全发现 | 位置 |
|---|---|---|
| 中危 | Documentation-only skill with unverifiable behavior 文档欺骗 | SKILL.md:1 |
| 中危 | Undeclared scheduled execution mechanism 权限提升 | SKILL.md:22 |
| 低危 | Memory file access without visibility into data handling 敏感访问 | SKILL.md:12 |
| 资源类型 | 声明权限 | 推断权限 | 状态 | 证据 |
|---|---|---|---|---|
| 文件系统 | NONE | WRITE | ✗ 越权 | SKILL.md describes '压缩冗余内容,清理过期信息' (compress redundant content, clean expired in… |
目录结构
1 文件 · 1.1 KB · 48 行 Markdown 1f · 48L
└─
SKILL.md
Markdown
安全亮点
✓ No network requests described in documentation
✓ No credential harvesting mentioned
✓ No base64, eval, or obfuscation patterns visible in docs
✓ Core concept (memory compression) is functionally legitimate