ClawHub
Back to skill

Security audit

Ui Cloner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed UI screenshot-to-skill generator with local file creation and packaging that fit its stated purpose.

Install this if you want a skill that creates a local design-system package from screenshots. Before using it, confirm the output directory, review generated files, and ensure the referenced packaging script path is trusted and exists on your machine.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
91% confidence
Finding
The skill directs the agent to execute a local Python script via a shell command to package output files. While packaging is related to the stated goal, invoking an arbitrary local script from a hard-coded filesystem path expands execution scope and creates risk if that script is modified, replaced, or unavailable, especially because the skill's main purpose is screenshot analysis rather than trusted local code execution.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases are broad enough to activate on common design-assistance requests such as 'copy this design' or 'reproduce this page,' which may cause the skill to run in situations where the user did not intend filesystem writes or skill generation. Overbroad activation increases the chance of unintended tool use, file creation, and downstream actions beyond simple design analysis.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill does not clearly disclose up front that it will create a directory tree, write multiple reference files, and package a .skill artifact on disk. This omission can mislead users about the operational impact of invoking the skill and reduces informed consent for persistent changes to the local environment.

Static analysis

No suspicious patterns detected.