可信 — 风险评分 5/100
上次扫描:1 天前 重新扫描
5 /100
lobster-attachment-inject
动态附件注入 — 在不修改system prompt的情况下注入动态内容。参考Claude Code的Attachment消息机制。
The skill is a documentation-only SKILL.md describing a dynamic attachment injection concept for AI agent token optimization, with no executable code, scripts, or concerning behavior.
技能名称lobster-attachment-inject
分析耗时20.1s
引擎pi
可以安装
No action needed. This is a pure documentation file explaining a design pattern for dynamic content injection.
资源类型声明权限推断权限状态证据
文件系统 READ NONE ✓ 一致 SKILL.md describes read patterns but contains no actual code

目录结构

1 文件 · 2.3 KB · 76 行
Markdown 1f · 76L
└─ 📝 SKILL.md Markdown 76L · 2.3 KB

安全亮点

✓ No executable scripts present — this is a documentation-only skill
✓ No network requests, credential access, or file I/O in actual code
✓ Bash snippets are simple grep/sed pipelines for metadata extraction, all benign
✓ No obfuscation, base64, or hidden functionality detected
✓ No sensitive paths (~/.ssh, ~/.aws, .env) accessed anywhere
✓ No credential harvesting or data exfiltration indicators