injection-defense
当系统提示需要防御提示注入、越狱攻击、社会工程、内容信任边界突破等安全威胁时调用此 Skill。适用于构建 AI Agent、聊天机器人、文档处理助手等任何接受外部输入的系统提示。不适用于纯内部工具调用场景或已完全隔离的沙箱环境,也不适用于 UI 布局或响应格式设计。
Source facts
- Repository
- kangarooking/system-prompt-skills
- Last source activity
- May 4, 2026 at 05:08
- Detected SKILL.md language
- Chinese
- Stars
- 178
- Forks
- 40
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.