ClawHub
Back to skill

Security audit

Notion Skill

Security checks for vulnerabilities and agentic risk

Overview

This Notion skill is a straightforward guide for using a local Notion CLI, with expected token-based access and no hidden execution or persistence.

Before installing, treat NOTION_API_KEY as a secret, share the Notion integration only with the pages or databases the agent needs, review schema diffs before allowing schema changes, and install any required Notion CLI from a trusted source.

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
  • 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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README tells users to export a live Notion integration token into an environment variable but gives no warning that the token is a sensitive secret, no guidance on avoiding shell history/log exposure, and no mention of least-privilege sharing. In a skill specifically designed to access and modify Notion content, mishandling this credential could let other local processes, logs, shell history, or copied commands expose the token and enable unauthorized access to shared pages and databases.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.