ClawHub
Back to skill

Security audit

Recipe Organize Drive Folder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Google Drive organization recipe that creates folders and moves user-specified files, with no hidden code or persistence beyond the Drive changes themselves.

Before using this recipe, confirm the file ID, old parent folder ID, and destination folder ID, and consider listing the affected files first. The commands can persistently reorganize Google Drive contents, which may affect how files are found or shared.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly instructs the agent to move existing Google Drive files by changing parent folders, which can alter a user's cloud file organization and potentially disrupt workflows, sharing expectations, or file discoverability. Although this appears to be a legitimate productivity recipe, it lacks safety guidance such as confirming target files/folders, warning about destructive reorganization effects, or requiring explicit user approval before modifying existing Drive structure.

Static analysis

No suspicious patterns detected.