Home / Skills / injection-defense
injection-defense
kangarooking/system-prompt-skillsSkill
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。
Why this score
This repo hosts 10 skills, so its 213 stars are split between them (about 21 each) for scoring.
Popularity score: 46/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit 252cd5251641, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneinjection-defense kangarooking/system-prompt-skills · Skill | 46 | ★ 213 | ≈38 always | 6mo ago |
| prompt-injection-defense seb1n/awesome-ai-agent-skills · Skill Both about defense and injection | 58 | ★ 218 | ≈109 always | 3mo ago |
| language-injection microsoft/data-formulator · Skill Both about injection | 84 | ★ 18k | ≈24 always | 16d ago |
| prompt-injection-assessment zero-lab-ai/skills · Skill Both about injection | 55 | ★ 82 | ≈69 always | 20d ago |
| injection-tester Stickman230/claude-pentest · Subagent Both about injection | 48 | ★ 121 | ≈71 in chat | 5mo ago |
| pydantic-ai-dependency-injection existential-birds/beagle · Skill Both about injection | 49 | ★ 84 | ≈53 always | 2mo ago |