ClawHub
Back to skill

Security audit

Folder Organizer

Security checks for vulnerabilities and agentic risk

Overview

This folder-organizer skill is purpose-aligned and includes safeguards, but users should only run it on explicit folders and confirm any file moves.

Install only if you are comfortable letting the agent inspect file names, sizes, paths, and timestamps in folders you specify. Start with a small target folder, choose a report directory, review the dry-run and validation output, and do not approve --apply or high-risk items unless the planned moves are clear.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill clearly instructs the agent to read directories, generate reports, and potentially write Markdown/JSON/CSV/log files, yet no permissions are declared. That mismatch can bypass user and platform expectations about what the skill may access or modify, especially in a file-management context that touches broad portions of a disk.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The default prompt and description are broad enough to trigger the skill for vague requests about cleaning up or organizing files, without clearly limiting the target path, operation scope, or requiring explicit confirmation. In a skill that can scan folders or disks, ambiguous activation increases the chance of unintended access to large or sensitive file collections.

Vague Triggers

Medium
Confidence
94% confidence
Finding
Enabling implicit invocation without narrowing context means the skill may activate automatically on loosely related requests, even though its function involves scanning, analyzing, and reorganizing filesystem content. Because this skill potentially touches broad disk or folder contents, accidental activation could expose sensitive metadata or cause unintended file movement recommendations at a much wider scope than the user intended.

Static analysis

No suspicious patterns detected.