ClawHub
Back to skill

Security audit

Frontend Design Pro — 专业前端设计规范

Security checks for vulnerabilities and agentic risk

Overview

This is a frontend design guidance skill with no executable code, persistence, credential use, or hidden data access.

Install this if you want opinionated frontend design defaults and review commands. Expect it to push specific style preferences, such as avoiding Inter/system-ui and applying its design rules during UI work; skip or disable it for projects where those design choices conflict with an existing design system.

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)

Natural-Language Policy Violations

Medium
Confidence
74% confidence
Finding
The manifest description is written entirely in Chinese and presents the skill behavior as Chinese-first without indicating that users may choose another language. Under the policy, forcing a specific language or locale without opt-in can be a natural-language policy violation.

Vague Triggers

Medium
Confidence
97% confidence
Finding
The listed natural-language triggers include broad phrases like '优化界面' and '让设计更好看', which overlap with common user requests and can activate the skill unintentionally. This creates prompt-scope confusion: the assistant may apply hidden stylistic rules or rewrite code beyond what the user requested, reducing predictability and control.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The execution rule says the skill should activate for broadly defined 'design-related requests', which can cause unintended invocation in many ordinary frontend/UI conversations. Over-broad activation can override user intent, inject unsolicited constraints, and increase the chance that the model follows skill instructions when the user did not explicitly ask for them.

Static analysis

No suspicious patterns detected.