ClawHub
Back to skill

Security audit

Minimalist Design System

Security checks for vulnerabilities and agentic risk

Overview

This is a design-system guidance skill with no executable code, persistence, credential access, or hidden data behavior.

Before installing, confirm that you want this minimalist design-system style to influence frontend work. For non-Chinese workflows, ask the agent to respond in your language and to apply the skill only when you explicitly request design-system, UI styling, Tailwind token, component library, or visual consistency work.

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 (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger scenario is broad enough to overlap with many ordinary frontend/UI requests, which can cause the skill to activate when the user did not specifically request this design-system behavior. In an agent setting, overbroad activation can steer responses unnecessarily, increasing the chance of irrelevant code changes, unwanted stylistic rewrites, or accidental override of a more appropriate skill.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill metadata and content are effectively Chinese-only and do not provide a language-selection mechanism or clear locale scoping. This can cause the skill to respond in an unexpected language, reducing transparency and potentially leading users to accept code or architectural guidance they cannot fully review.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
SQP-3 applies to all file types and covers language or locale policy violations. This markdown specification presents all instructions in Chinese only, with no opt-in, alternative language option, or justification that the skill is region-specific, which can force a specific language on users.

Static analysis

No suspicious patterns detected.