ClawHub
Back to skill

Security audit

Notion

Security checks across malware telemetry and agentic risk

Overview

This appears to be a disclosed Notion connector skill with broad read/write capability, but no evidence of hidden, destructive, or unrelated behavior.

Install only if you intend to let Codex use your connected Notion account through OOMOL. Give explicit instructions for any create or update task, and review proposed Notion changes before allowing them to run.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger text instructs the agent to use this skill for ANY Notion request and instead of calling the API directly, which is overly broad and can cause unintended invocation. In an agentic system, broad routing rules increase the chance that the skill is selected in contexts the user did not clearly intend, including write-capable workflows, which raises the risk of accidental data exposure or modification.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.