agent-craft
AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体
0Tools
4Findings
181Stars
Mar 22, 2026Last Scanned
⚠3 high · 1 low findings detected
⚡Prompt Injection
Prompt & context manipulation attacks
PI-DIRDirect Input Injection
Injection via tool descriptions and parameter fields
GAP-001Prompt Injection Coverage GapMissing detection coverage for emerging prompt injection attack variants not addressed by current rules
PI-INDIndirect / Gateway Injection
Hidden instructions via external content and tool responses
PI-CTXContext Manipulation
Context window saturation and prior-approval exploitation
PI-ENCEncoding & Obfuscation
Payload hiding via invisible chars, base64, schema fields
PI-TPLTemplate & Output Poisoning
Injection via prompt templates and runtime tool output