indirect-injection-detection
Tencent · Development
检测间接提示注入（目标劫持）。隐藏在“外部”内容（文档、RAG、网页）中的指令，被代理处理时可能触发。适用于代理接收文档/RAG/网页/文件输入时。
Detect indirect prompt injection (goal hijack). Instructions hidden in "external" content (documents, RAG, web) that the agent processes. Use when the agent has document/RAG/web/file input.
npx skills add https://github.com/Tencent/AI-Infra-Guard --skill indirect-injection-detection
星标 3882 · 安装量 0