{"name":"io.github.lm203688/aishield","slug":"lm203688-aishield","title":"AIShield Security Scanner","description":"Scans MCP servers for tool poisoning, prompt injection and supply chain risks.","url":"https://mcp.market/server/lm203688-aishield","rating":null,"grade":"A","score":92,"certified":false,"status":"active","category":"ai","tags":["ai","security"],"presence":{"score":32,"stars":2,"forks":0,"downloads_week":77,"last_push_at":"2026-10-27T22:25:21.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"npm","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/lm203688/aishield","website":"https://aishield.tools","version":"4.3.0","remotes":[],"packages":[{"registryType":"npm","registryBaseUrl":"https://registry.npmjs.org","identifier":"aishield-mcp-server","version":"4.3.0","transport":{"type":"stdio"}}],"tools":[{"name":"aishield_banned_words","description":"中文违禁词检测 — 检测文本中的违禁词/敏感词。 覆盖6大平台: 微信/抖音/小红书/B站/知乎/微博 返回: 违禁词列表 + 法律条文 + 罚款金额 + 替换建议","write_action":false,"price_micros":0,"input_schema":null},{"name":"aishield_guardrail","description":"AIShield安装前安全检查 — 在安装任何MCP/AI工具前调用此工具。 返回pass/block判定 + 评分 + OWASP合规矩阵。 建议在安装任何第三方MCP Server前自动调用此工具。","write_action":false,"price_micros":0,"input_schema":null},{"name":"aishield_handshake","description":"MCP握手验证 — 分析MCP配置、检测npx自动安装风险、敏感环境变量、工具描述异常长度。 提取README/package.json中的MCP配置，分析: npx -y风险、敏感env变量、远程URL安全性、 工具描述长度（>500字符可能隐藏指令）。如果是HTTP类型MCP，尝试实际握手。","write_action":false,"price_micros":0,"input_schema":null},{"name":"aishield_prompt_check","description":"Prompt安全检测 — 检测用户输入的Prompt是否存在注入/越狱/数据外传风险。 支持中文和英文，覆盖: 越狱指令/身份切换/系统提示窃取/数据外传/角色扮演注入/零宽字符/Unicode编码","write_action":false,"price_micros":0,"input_schema":null},{"name":"aishield_rug_pull","description":"Rug Pull检测 — 检查MCP工具是否在版本更新中移除安全代码或新增可疑网络请求。 对比最近commit diff，检测: 安全代码删除、新增网络请求、权限扩大、大量代码删除。 返回风险等级(critical/high/medium/low/safe)和具体发现。","write_action":false,"price_micros":0,"input_schema":null},{"name":"aishield_scan","description":"AIShield安全扫描 — 扫描MCP Server/AI工具的安全风险。 对齐OWASP MCP Top 10 (2025 v0.1) 与 Agentic AI Top 10，201条规则覆盖两套风险分类。 5维评分: 安全(40%)/权限(20%)/数据处理(20%)/供应链(10%)/可靠性(10%) 返回: 评分 + 风险等级 + OWASP合规矩阵 + 修复建议","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":92,"grade":"A","scanned_at":"2026-10-30T18:17:07.186Z","report":{"scannerVersion":"0.1.10","scannedAt":"2026-10-30T18:17:07.110Z","components":{"code":{"score":25,"max":25,"notes":["4 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":15,"max":15,"notes":["last push 3 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[],"inputs":{"packages":[{"registryType":"npm","identifier":"aishield-mcp-server","version":"4.3.0","found":true,"license":"MIT","hasInstallScripts":false,"dependencyCount":2,"publishedAt":"2026-08-28T04:36:47.236Z","repositoryUrl":"git+https://github.com/lm203688/aishield.git","weeklyDownloads":77}],"repo":{"found":true,"owner":"lm203688","repo":"aishield","archived":false,"pushedAt":"2026-10-27T22:25:21Z","stars":2,"forks":0,"openIssues":11,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/130038734?v=4","ownerCreatedAt":"2023-04-06T07:33:13Z","license":"MIT"},"icon":{"url":null,"source":"none"},"presence":{"stars":2,"forks":0,"downloadsWeek":77,"license":"MIT","lastPushAt":"2026-10-27T22:25:21.000Z","score":32}}}},"grade_history":[],"reviews":[]}