ClawHub
Back to skill

Security audit

Web构件工作室

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only frontend artifact generation skill with some overbroad generic guidance, but no hidden executable installer, persistence mechanism, or artifact-backed malicious behavior.

Install only if you want an agent to generate frontend artifacts in your workspace. Keep generated files scoped to the intended project directory, review any npm/npx or external API steps before running them, do not put secrets in client-side code, and avoid storing real personal data such as phone or email in localStorage unless you add notice, retention limits, and a clear way to clear it.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

Medium
Confidence
78% confidence
Finding
The skill expands from a narrowly described frontend artifact generator into generic file processing, API integration, and command execution capabilities. In an agent setting, this broader capability framing can encourage unsafe use of exec or external-service interactions outside the original trust boundary, increasing the chance of command injection, credential misuse, or unintended data exfiltration in downstream use.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The example persists user registration data including name, email, and phone to localStorage without a clear privacy warning, retention policy, or guidance on handling shared-device risks. localStorage is long-lived and readable by any script running on the same origin, so storing personal data there can increase exposure if the generated artifact later includes XSS or is used in a less-trusted environment.

Static analysis

No suspicious patterns detected.