ClawHub
Back to skill

Security audit

前端设计-免费版

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a frontend design guide, but it asks for command execution and file-write capability while also describing itself as Markdown-only with no exec requirement.

Install only if you are comfortable with a design helper that may receive command-execution and file-write authority. Prefer using it in a constrained project workspace and require explicit confirmation before it runs shell commands or modifies files.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The skill documentation claims it is a pure Markdown skill that does not require exec, but the manifest still grants exec capability. This mismatch can cause an agent or user to trust the skill as non-executing while it actually has permission to run commands, increasing the risk of unexpected command execution if later prompts or modifications invoke the tool.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger condition is broad enough to match many ordinary design or creative requests, which can cause the skill to activate in situations beyond its narrowly intended scope. Over-broad triggering increases the chance that the agent grants this skill's tool access, including write/exec capability, in contexts where the user did not specifically request it.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.