中文 EN

Scan Report

Scan New Files

⚠ Low Risk — Risk Score 15/100
Last scan:20 hr ago Rescan
15 /100
uplo-compliance
AI-powered compliance intelligence spanning legal, financial, and government regulatory requirements
This is a legitimate compliance intelligence skill with documented MCP server integration and external API connectivity. Minor supply chain concern from unpinned npx dependency.
Skill Nameuplo-compliance
Duration37.0s
Enginepi
✓
Safe to install
Pin the @agentdocs1/mcp-server package to a specific version (e.g., npx -y @agentdocs1/[email protected]) to prevent supply chain attacks from malicious updates.

Findings 2 items

Severity Finding Location
Low
Unpinned MCP Server Dependency Supply Chain
The skill uses 'npx -y @agentdocs1/mcp-server' without pinning to a specific version. This allows the package to be updated to a potentially malicious version between executions.
"args": ["-y", "@agentdocs1/mcp-server", "--http"]
→ Pin to a specific version: npx -y @agentdocs1/[email protected]
 skill.json:18
Low
External API Key Required Sensitive Access
The skill requires users to provide an API_KEY for the UPLO service. Users should ensure this key has minimal required permissions.
"api_key": {"type": "string", "required": true, "secret": true}
→ Use a scoped API key with least privilege access to the compliance knowledge base only
 skill.json:14
ResourceDeclaredInferredStatusEvidence
Network READ READ ✓ Aligned skill.json:17-21 - MCP server connects to external UPLO instance
Skill Invoke WRITE WRITE ✓ Aligned skill.json:25-28 - MCP tools (search_knowledge, search_with_context, etc.)
Filesystem NONE NONE — No filesystem operations detected in documentation
Shell NONE NONE — npx command is for package execution, not user shell access
10 findings
🔗
Medium External URL 外部 URL
https://img.shields.io/badge/ClawHub-uplo-compliance-blue
README.md:5
🔗
Medium External URL 外部 URL
https://clawhub.com/skills/uplo-compliance
README.md:5
🔗
Medium External URL 外部 URL
https://img.shields.io/badge/MCP-21_tools-green
README.md:6
🔗
Medium External URL 外部 URL
https://img.shields.io/badge/schemas-21-orange
README.md:7
🔗
Medium External URL 外部 URL
https://uplo.ai/schemas
README.md:7
🔗
Medium External URL 外部 URL
https://your-instance.uplo.ai
README.md:24
🔗
Medium External URL 外部 URL
https://clawhub.com/skills/uplo-environmental
README.md:62
🔗
Medium External URL 外部 URL
https://clawhub.com/skills/uplo-government
README.md:63
🔗
Medium External URL 外部 URL
https://clawhub.com/skills/uplo-knowledge-management
README.md:64
🔗
Medium External URL 外部 URL
https://app.uplo.ai
skill.json:17

File Tree

4 files · 11.7 KB · 231 lines
Markdown 3f · 182L JSON 1f · 49L
├─ 📝 identity-patch.md Markdown 9L · 1.8 KB
├─ 📝 README.md Markdown 72L · 2.8 KB
├─ 📋 skill.json JSON 49L · 1.3 KB
└─ 📝 SKILL.md Markdown 101L · 5.9 KB

Dependencies 1 items

PackageVersionSourceKnown VulnsNotes
@agentdocs1/mcp-server * npm No Version not pinned - supply chain risk

Security Positives

✓ No shell execution or subprocess calls to user environment
✓ No credential harvesting beyond what the service requires
✓ No base64 encoding, obfuscation, or anti-analysis patterns
✓ Documentation clearly describes all MCP tools and their purpose
✓ No access to sensitive local paths (~/.ssh, ~/.aws, .env)
✓ API key is marked as secret in skill.json config