ClawHub
Back to skill

Security audit

Frontend Design

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward frontend design helper with no evidence of hidden execution, persistence, credential use, or unrelated data access.

Install this if you want an opinionated frontend design assistant. Be aware it may activate for broad web design requests and may push bold visual choices, so review generated UI code and dependencies as you normally would.

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
94% confidence
Finding
The skill description is broad enough to trigger on many routine frontend requests, which increases the chance this skill is invoked when a narrower or safer skill would be more appropriate. Overly broad activation can cause unintended tool selection, expanding the skill’s influence and making downstream prompt behavior harder to constrain or audit.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The manifest activates on generic phrases such as "网页设计", "页面开发", "web design", and "build page" without any stated scope limitations or exclusion conditions. These triggers are broad enough to match everyday user requests, increasing the risk of unintended invocation.

Natural-Language Policy Violations

Low
Confidence
75% confidence
Finding
The file presents the primary description in Chinese and mixes bilingual trigger phrases, but does not state whether the skill will respond in a user-selected language. This can create an implicit language preference without documented opt-in or locale justification.

Static analysis

No suspicious patterns detected.