$ loading_
Catches leaked credentials and PII in outbound LLM prompts
复制安装指令，让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "io.github.4hmetuyar/prompt-leak-scanner" MCP 服务： 执行：claude mcp add 'io-github-4hmetuyar-prompt-leak-scanner' -- npx -y @guardbee/mcp-prompt-leak-scanner
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
KVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit log
Scans RAG content/scraped pages for indirect prompt injection
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
Scans RAG content/scraped pages for indirect prompt injection