ClawHub
Back to skill

Security audit

Design For Beauty

Security checks for vulnerabilities and agentic risk

Overview

This is a design-assistance skill that reads bundled design reference documents and gives UI direction, with no evidence of hidden execution, persistence, credential access, or destructive behavior.

Before installing, note that this skill may activate for many design or frontend-polish requests and may steer the agent to use its design-reference workflow. From the inspected artifact, that workflow appears read-only and purpose-aligned, though the referenced bundled design files were not present in this workspace.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation description is broad enough to trigger on many ordinary design or frontend requests, increasing the chance this skill is selected when a narrower or safer skill would be more appropriate. Over-broad routing can cause unintended file access to bundled references and steer the agent into behavior the user did not explicitly request, which is a scope-control weakness even if not directly malicious.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
58% confidence
Finding

The description includes Chinese trigger examples alongside English ones, but it does not actually require a specific output language or locale. Because the file does not instruct the skill to force a language, this is at most a weak policy concern rather than a clear violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.