可信 — 风险评分 5/100
上次扫描:20 小时前 重新扫描
5 /100
uplo-clinical
AI-powered clinical operations intelligence spanning pharmaceutical development and healthcare delivery
UPLO Clinical is a legitimate clinical operations knowledge management skill that connects to a documented UPLO MCP server via standard configuration—no executable scripts, no shell access, and no suspicious behaviors beyond expected SaaS connectivity.
技能名称uplo-clinical
分析耗时27.7s
引擎pi
可以安装
Approve for use. The skill is a pure documentation/configuration package for a clinical SaaS product. No action required beyond standard API key security practices.

安全发现 1 项

严重性 安全发现 位置
低危
Third-party MCP server dependency 供应链
The skill relies on @agentdocs1/mcp-server package from npm. This is a standard MCP pattern and the dependency is explicitly declared.
@agentdocs1/mcp-server
→ Verify npm package authenticity before use; this is standard practice for MCP integrations.
skill.json:21
资源类型声明权限推断权限状态证据
文件系统 NONE NONE No file access in any files
网络访问 READ READ ✓ 一致 skill.json:17 - MCP server connects to configured UPLO instance
命令执行 NONE NONE No shell execution found
环境变量 NONE NONE No environment variable access
技能调用 NONE NONE No inter-skill invocation
剪贴板 NONE NONE No clipboard access
浏览器 NONE NONE No browser automation
数据库 NONE NONE No direct DB access
10 项发现
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/ClawHub-uplo-clinical-blue
README.md:5
🔗
中危 外部 URL 外部 URL
https://clawhub.com/skills/uplo-clinical
README.md:5
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/MCP-21_tools-green
README.md:6
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/schemas-15-orange
README.md:7
🔗
中危 外部 URL 外部 URL
https://uplo.ai/schemas
README.md:7
🔗
中危 外部 URL 外部 URL
https://your-instance.uplo.ai
README.md:24
🔗
中危 外部 URL 外部 URL
https://clawhub.com/skills/uplo-healthcare
README.md:61
🔗
中危 外部 URL 外部 URL
https://clawhub.com/skills/uplo-knowledge-management
README.md:62
🔗
中危 外部 URL 外部 URL
https://clawhub.com/skills/uplo-pharma
README.md:63
🔗
中危 外部 URL 外部 URL
https://app.uplo.ai
skill.json:17

目录结构

4 文件 · 11.5 KB · 224 行
Markdown 3f · 175L JSON 1f · 49L
├─ 📝 identity-patch.md Markdown 9L · 1.8 KB
├─ 📝 README.md Markdown 71L · 2.7 KB
├─ 📋 skill.json JSON 49L · 1.2 KB
└─ 📝 SKILL.md Markdown 95L · 5.8 KB

依赖分析 1 项

包名版本来源已知漏洞备注
@agentdocs1/mcp-server latest npm Pinned version recommended for production use

安全亮点

✓ No executable scripts present—pure configuration and documentation
✓ All capabilities are explicitly declared in SKILL.md and skill.json
✓ No shell or filesystem access requests
✓ API key properly marked as secret in skill.json config
✓ No obfuscation or base64-encoded payloads
✓ No credential harvesting beyond what's required for service auth
✓ No suspicious network patterns (only documented UPLO service URLs)
✓ Clear documentation of what the MCP server does
✓ No sensitive files accessed (no .ssh, .env, or config file scanning)