Security audit

前端设计-专业版

Security checks across malware telemetry and agentic risk

Overview

This frontend-design skill is mostly aligned with generating UI and design-system files, but it asks for command execution, workspace writes, network/API use, and credentials without enough scope detail.

Review before installing. Use this only in a project workspace where generating or modifying frontend files is intended, avoid entering unrelated API keys or broad credentials, keep license/API values in environment variables, and inspect any command or generated output path before allowing execution.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (5)

Context-Inappropriate Capability

Medium

Confidence: 87% confidence
Finding: The skill advertises API/network usage despite being presented as a frontend design tool, creating capability creep that is not clearly tied to its stated purpose. This can mislead users into granting broader permissions or exposing credentials for functions they do not expect, increasing the attack surface for data exfiltration or unauthorized remote access.

Context-Inappropriate Capability

Medium

Confidence: 91% confidence
Finding: The documentation asks users to configure API keys and establish API-backed operation without clearly mapping that need to the declared design functionality. Unnecessary credential collection in a markdown skill is dangerous because it normalizes secret handling for opaque behavior and may lead users to provide sensitive tokens that could be misused.

Context-Inappropriate Capability

Medium

Confidence: 90% confidence
Finding: The getting-started section instructs users to initialize API connections and use credentials even though the rest of the skill is framed as local design assistance. In context, this makes the skill more dangerous because a broad creative/design skill can be invoked frequently, increasing chances that users will follow opaque connection steps and expose secrets unnecessarily.

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The activation/use language is very broad and overlaps with common design and creative requests, which can cause the skill to trigger in many contexts beyond its intended scope. Over-broad invocation increases the chance that users will unknowingly enable exec/write-capable behavior during routine requests, making otherwise moderate capabilities more risky.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The markdown describes generating files and executing commands, but it does not provide a prominent warning that these actions may modify the local workspace. This is dangerous because users may treat the skill as advisory text while it encourages operational steps that can overwrite files, create artifacts, or run tools with side effects.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.