ClawHub

Notion Manager

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a Notion helper that openly uses a Notion token to add or manage user-directed content, with no evidence of hidden exfiltration or unrelated behavior.

Install only if you intend to let the agent access and modify the selected Notion workspace/page/database. Use a least-privilege Notion integration, connect only the specific resources needed, and confirm write or undo/delete actions before running them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly requires a Notion API key and is designed to make outbound API calls, yet it declares no permissions despite having network capability. This undermines transparency and policy enforcement, making it easier for a write-capable integration to be invoked without users or platforms clearly understanding that external network access occurs.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill supports write-capable operations such as createPage, updatePage, appendBlocks, and createDataSource, but the description does not warn that these actions can modify or expand workspace content. In a SaaS workflow setting, this increases the risk of accidental destructive changes, data sprawl, or unauthorized content manipulation if the skill is invoked with broad integration access.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal