ClawHub
Back to skill

Security audit

前端设计

Security checks for vulnerabilities and agentic risk

Overview

This is a frontend design guidance skill with no executable code, persistence, credential handling, or hidden high-impact behavior.

Install this if you want a strongly opinionated Chinese-language frontend design assistant. Review whether its broad frontend triggers and Chinese output style fit your workflow, especially if you prefer another language or only want narrowly scoped UI help.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill is written to operate entirely in Chinese without offering a language-selection mechanism, which can override the user's preferred language or produce outputs the user cannot review accurately. This creates a safety and usability risk because misunderstandings in code, requirements, or generated UI text can lead to incorrect implementation and reduced user oversight.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger conditions are very broad and can activate on generic requests like 'help me write a webpage' or 'make a frontend page,' causing this skill to take over many ordinary web-related prompts. Overly broad routing increases the chance of misclassification, reduces principle-of-least-surprise behavior, and may suppress more appropriate skills or user intent handling.

Static analysis

No suspicious patterns detected.