ClawHub
Back to skill

Security audit

notion-test

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only Notion API skill whose credential use and workspace write examples match its stated purpose.

Install only if you want an agent to use a Notion integration token. Use a dedicated Notion integration, share only the pages or databases the agent should access, review create/update/add-block commands before running them, and keep the local API key file private.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill documents multiple write-capable operations against the live Notion API, including creating pages, creating data sources, updating properties, and appending blocks, but it does not clearly warn that these commands will modify remote workspace content. In an agent-skill context, omission of mutation warnings increases the chance of unintended destructive or unauthorized changes when a user or agent treats examples as safe read-only operations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal