中文 EN

Scan Report

Scan New Files

⚠ Low Risk — Risk Score 15/100
Last scan:19 hr ago Rescan
15 /100
uplo-agriculture
AI-powered agricultural knowledge management. Search crop management records, livestock data, compliance documentation, and sustainability reports.
This is a legitimate agricultural knowledge management skill using the MCP protocol with no malicious code present, though the unversioned npx package dependency poses a minor supply chain risk.
Skill Nameuplo-agriculture
Duration52.4s
Enginepi
✓
Safe to install
Consider pinning the MCP server version (e.g., `@agentdocs1/[email protected]` instead of `@agentdocs1/mcp-server`) to prevent unexpected updates. Otherwise safe to use.

Findings 1 items

Severity Finding Location
Low
Unpinned MCP server package version Supply Chain
The skill installs @agentdocs1/mcp-server using npx -y without version pinning, allowing any version to be installed. This could lead to unexpected behavior if the package is updated.
"args": ["-y", "@agentdocs1/mcp-server", "--http"]
→ Pin the package version: @agentdocs1/[email protected] or @agentdocs1/[email protected]
 skill.json:22
ResourceDeclaredInferredStatusEvidence
Network READ READ ✓ Aligned HTTP transport to configured UPLO endpoint via MCP protocol
Environment READ READ ✓ Aligned Reads AGENTDOCS_URL and API_KEY from config/env
Filesystem NONE NONE — No filesystem access declared or observed
Shell NONE NONE — No shell commands executed; mcporter calls are tool invocations
Skill Invoke WRITE WRITE ✓ Aligned Uses mcporter to invoke UPLO MCP tools
10 findings
🔗
Medium External URL 外部 URL
https://img.shields.io/badge/ClawHub-uplo-agriculture-blue
README.md:5
🔗
Medium External URL 外部 URL
https://clawhub.com/skills/uplo-agriculture
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-4-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:60
🔗
Medium External URL 外部 URL
https://clawhub.com/skills/uplo-knowledge-management
README.md:61
🔗
Medium External URL 外部 URL
https://clawhub.com/skills/uplo-sustainability
README.md:62
🔗
Medium External URL 外部 URL
https://app.uplo.ai
skill.json:17

File Tree

4 files · 7.2 KB · 185 lines
Markdown 3f · 136L JSON 1f · 49L
├─ 📝 identity-patch.md Markdown 9L · 1.7 KB
├─ 📝 README.md Markdown 70L · 2.7 KB
├─ 📋 skill.json JSON 49L · 1.2 KB
└─ 📝 SKILL.md Markdown 57L · 1.5 KB

Dependencies 1 items

PackageVersionSourceKnown VulnsNotes
@agentdocs1/mcp-server unpinned npx No Package version not specified - any version may be installed

Security Positives

✓ Well-documented SKILL.md with clear scope and purpose
✓ API key declared as secret in config, not hardcoded
✓ No direct filesystem, shell, or sensitive path access
✓ No credential harvesting or data exfiltration code
✓ No obfuscation patterns (base64, eval, etc.)
✓ Uses legitimate MCP protocol standard
✓ No suspicious network connections beyond declared MCP endpoint
✓ Classification tier controls documented