$ loading_
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
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.GuardBee/tool-poisoning-scanner" MCP 服务： 执行：claude mcp add 'io-github-guardbee-tool-poisoning-scanner' -- npx -y @guardbee/mcp-tool-poisoning-scanner
Catches leaked credentials and PII in outbound LLM prompts
Scans files for leaked secrets and API keys
GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
Bundle of secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligence
Finds PII and credentials in PDFs, screenshots and scanned documents