4hmetuyar
收录自公开来源。所有者登录后即可认领。
共 27 项
4hmetuyar 1slopsquat-scannerChecks declared npm/PyPI dependencies against real registries to catch slopsquattingMCPNode.js
4hmetuyar 1unbounded-consumption-auditorScans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)MCPNode.js模型
4hmetuyar 1rug-pull-detectorBaselines an MCP server's tools and detects tool-definition changes after approvalMCPNode.js
4hmetuyar 1vector-store-scannerProbes vector-database endpoints for unauthenticated exposure of embeddings/RAG dataMCPNode.js数据库模型
4hmetuyar 1security-suiteBundle of secret-scanner, dependency-auditor, ssl-inspector, and dns-intelligenceMCPNode.js安全
4hmetuyar 1ssl-inspectorTLS certificate/cipher/protocol inspectionMCPNode.js
4hmetuyar 1toxic-flow-auditorFinds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egressMCPNode.js
4hmetuyar 1vulnerability-scannerTriggers GuardBee scans, queries findings, AI-assisted remediation guidanceMCPNode.js安全
4hmetuyar 1model-scannerScans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risksMCPNode.js文件
4hmetuyar 1prompt-leak-scannerCatches leaked credentials and PII in outbound LLM promptsMCPNode.js模型
4hmetuyar 1tool-poisoning-scannerScans MCP tool definitions for hidden instructions and confused-deputy sinksMCPNode.js
4hmetuyar 1oauth-auditorScans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audienceMCPNode.js
4hmetuyar 1prompt-injection-scannerScans RAG content/scraped pages for indirect prompt injectionMCPNode.js
4hmetuyar 1secret-scannerScans files for leaked secrets and API keysMCPNode.js文件
4hmetuyar 1security-proxyMCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit logMCPNode.js安全
4hmetuyar 1memory-poisoning-scannerScans agent code for untrusted input poisoning persistent cross-session memoryMCPNode.js记忆
4hmetuyar 1dns-intelligenceDNS record enumeration, misconfiguration and dangling-subdomain detectionMCPNode.js
4hmetuyar 1llm-redteamActive jailbreak/extraction/obfuscation red-teaming for live LLM endpointsMCPNode.js模型
4hmetuyar 1mcp-config-auditorScans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquatsMCPNode.js
4hmetuyar 1elicitation-auditorMCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLsMCPNode.js
4hmetuyar 1agent-graph-auditorFinds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphsMCPNode.js
4hmetuyar 1ai-code-scannerScans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injectionMCPNode.js模型
4hmetuyar 1db-gatewayKVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit logMCPNode.js数据库法律模型
4hmetuyar 1dependency-auditorCVE scanning for npm/pip/cargo dependencies via OSVMCPNode.js安全