Honeypot framework for building decoy MCP tools to detect prompt injection and malicious agent behavior.
接入配置
该项目没有提供统一的启动命令，请按源码仓库的说明安装。
相关推荐
更多- MMastyfmastyf-ai官方Security proxy for LLMs and MCP that blocks prompt injection, SSRF, injection attacks and credential exfiltration.安全21 仓库星标
- KKoma Gate MCPswnotmetal官方Classifies input for prompt injection and out-of-scope content with the Koma Gate LLM-based classifier.安全13 仓库星标
- SShellWardjnMetaCode国内厂商让智能体检测提示注入、追踪敏感数据流、拦截危险命令并识别个人信息，也可检查 AI 项目的数据出境与密钥合规。安全139 仓库星标
- RReasonGatecgrtmlGateway for stdio MCP servers that blocks tool calls whose destination or content came from untrusted tool results, with an auditable reason for each decision.安全16 仓库星标
- AAletheia MCPvikasny30Filters agent tool calls before execution, blocking scope creep such as credential reads, SSRF, destructive shell or SQL commands, and prompt injection.安全12 仓库星标
- AAperion ShieldAperionLocal proxy that wraps MCP servers and blocks destructive calls such as dropping tables or recursive deletes, pins tool catalogs and scans for tool poisoning.安全11 仓库星标