ClawHub
Back to skill

Security audit

open-notion

Security checks for vulnerabilities and agentic risk

Overview

This skill only opens Notion in Brave and is clear that it should not handle credentials or change workspace content.

Install this only if you are comfortable with an agent focusing Brave and opening your existing Notion session when you ask for Notion. Review the visible browser state before sharing your screen, since an authenticated workspace may appear, but the skill does not instruct the agent to enter credentials or modify Notion content.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger description includes broad phrases like 'open Notion', 'go to Notion', and 'access their Notion workspace', which are common natural-language requests and can cause the skill to be invoked in situations the user did not specifically intend for this exact automation. In this skill's context, unintended invocation is somewhat limited by the narrow action scope, but it could still unexpectedly focus the browser, reuse an authenticated tab, or navigate to a logged-in workspace, creating privacy and UX risks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.