Summary
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。
kangarooking/system-prompt-skills
当系统提示需要防御提示注?
npx skills add kangarooking/system-prompt-skills --skill 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。
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Comprehensive guide for dependency injection (DI) in Golang. Covers why DI matters (testability…
36.9K installs>- SQL injection playbook. Use when input reaches SQL queries, authentication logic, sorting, f…
3.3K installs>- Entry P1 category router for injection testing. Use when routing between XSS, SQLi, SSRF, XX…
3K installs>- SSTI playbook. Use when template expressions, server-side rendering, preview features, or te…
3K installs>- LLM prompt injection playbook. Use when testing AI/LLM applications for direct injection, in…
3K installs>- Command injection playbook. Use when user input may reach shell commands, process execution,…
3K installsOther skills from kangarooking/system-prompt-skills · top by installs.
npx skills add kangarooking/system-prompt-skills
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
main
Files included with this skill beyond the listing page.
SKILL.md
5,792 B
SUMMARY.md
389 B
Claude Chrome 部署五层防御链(criticalinjectiondefense → socialengineeringdefense),Claude for Word 将文档正文、批注、修订全部标记为不可信,ChatGPT Agent 对屏幕指令实施钓鱼检测,Claude Web 对用户记忆中的可疑指令主动忽略,Grok 明令禁止使用指令本身的术语。核心模式:多层纵深、规则不可变、内容分级、反泄露元规则。
{{secret_name}} 模式)。