ClawHub
Back to skill

Security audit

Frontend Design

Security checks for vulnerabilities and agentic risk

Overview

This is a frontend design guidance skill with broad styling instructions but no hidden code, persistence, credential use, or destructive behavior.

Install this if you want agents to apply opinionated, high-design frontend direction. Be aware it may affect routine frontend work because its activation scope is broad and its style guidance is assertive.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill’s activation description is extremely broad, covering websites, landing pages, dashboards, components, layouts, applications, and general UI beautification. This can cause the agent to invoke the skill for a wide range of ordinary frontend tasks, increasing prompt-surface takeover risk and making it easier for this skill’s strong stylistic instructions to override more task-specific or safer behaviors.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.