7건 · 관련도순
Defend AI systems against prompt injection and indirect prompt attacks using input controls, tool permissions, output validation, and isolation boundaries.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audits legal AI skills, prompts, workflows, MCP/tool instructions, and agent packages for prompt injection, malicious instructions, unsafe scripts, suspicious metadata, credential exposure, exfiltration paths, persistence mechanisms, and supply-chain risk. Use before installing, importing, publishing, promoting, modifying, or trusting third-party or generated AI skills and legal workflows. Do not use as a generic code review unless skill trust, workflow safety, prompt injection, or supply-chain hygiene is in scope.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Secure skill template with prompt injection defenses. Copy this template when creating new skills.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
When scoring whether an agent response defended against an injection — treated untrusted content as data, refused role-takeover, ignored fake boundaries. Inverted axis; never auto-gates.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use this skill whenever user-controlled input flows into a MongoDB query, filter, or update. Trigger words: NoSQL Injection, ユーザー入力, req.body, クエリに渡す, find, filter, spread, $where, 検索条件, security review.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.