什么是 pentest-ai-llm-security?
AI/LLM 应用程序安全测试 — 根据 OWASP LLM Top 10 的提示注入、越狱、数据泄露和不安全输出处理。 来源:jd-opensource/joysafeter。
AI/LLM 应用程序安全测试 — 根据 OWASP LLM Top 10 的提示注入、越狱、数据泄露和不安全输出处理。
通过命令行快速安装 pentest-ai-llm-security AI 技能到你的开发环境
来源:jd-opensource/joysafeter。
Purpose AI-integrated applications introduce entirely new attack surfaces. Prompt injection is the "SQLi of AI." Neither Shannon nor any existing skill addresses this domain. OWASP LLM Top 10 (2025) defines the methodology.
| LLM01 Prompt Injection | Direct and indirect injection | ✅ | | LLM02 Sensitive Information Disclosure | Data exfiltration, PII leakage | ✅ | | LLM03 Supply Chain | Model provenance, plugin trust | ✅ | | LLM04 Data and Model Poisoning | Training data integrity | ✅ | | LLM05 Improper Output Handling | XSS/SQLi via LLM output | ✅ |
| LLM06 Excessive Agency | Unauthorized tool use | ✅ | | LLM07 System Prompt Leakage | System prompt extraction | ✅ | | LLM08 Vector and Embedding Weaknesses | RAG poisoning | ✅ | | LLM09 Misinformation | Hallucination exploitation | ✅ | | LLM10 Unbounded Consumption | Resource exhaustion | ✅ |
为搜索与 AI 引用准备的稳定字段与命令。
npx skills add https://github.com/jd-opensource/joysafeter --skill pentest-ai-llm-securityAI/LLM 应用程序安全测试 — 根据 OWASP LLM Top 10 的提示注入、越狱、数据泄露和不安全输出处理。 来源:jd-opensource/joysafeter。
打开你的终端或命令行工具(如 Terminal、iTerm、Windows Terminal 等) 复制并运行以下命令:npx skills add https://github.com/jd-opensource/joysafeter --skill pentest-ai-llm-security 安装完成后,技能将自动配置到你的 AI 编程环境中,可以在 Claude Code、Cursor 或 OpenClaw 中使用
https://github.com/jd-opensource/joysafeter