Security audit

HTML设计工具专业版

Security checks for vulnerabilities and agentic risk

Overview

This skill is a design-system helper that uses local file and command access for HTML/CSS generation, with no evidence of hidden persistence, credential theft, or automatic data exfiltration.

Installers should treat this as a local design-generation skill with broad file and command authority. Review any generated or suggested Python, Node, npm, ping, or integration commands before allowing execution, and only configure third-party API keys when intentionally connecting a design platform.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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)

Context-Inappropriate Capability

Medium

Confidence: 89% confidence
Finding: The skill states that no extra API key is needed and that local tooling is sufficient, yet elsewhere advertises external service integration through standardized APIs. This inconsistency can mislead operators about trust boundaries, data egress, and credential requirements, increasing the risk that users enable or route sensitive data to external services without appropriate review.

Intent-Code Divergence

Medium

Confidence: 92% confidence
Finding: The dependency and API key sections claim the skill is local-only and needs no extra API key, but later sections describe external API integration as a core capability. In an agent setting, this kind of documentation mismatch is security-relevant because reviewers may approve execution under a false assumption that there is no outbound communication or credential handling.

Static analysis

No suspicious patterns detected.