Security audit

Vue Toolkit Free

Security checks across malware telemetry and agentic risk

Overview

This Vue guidance skill is mostly educational, but it requests broad write and shell execution authority without clear limits or user-control safeguards.

Install only if you are comfortable with a Vue helper that may be routed into broad development tasks and has write/shell authority. Prefer using it in a project workspace where you can review file changes and commands before they run; it does not show evidence of theft, persistence, or destructive intent, but its authority is broader than its documentation safely explains.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Behavioral ASTexec() Call, eval() Call, Dynamic Import
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Context-Inappropriate Capability

Medium

Confidence: 94% confidence
Finding: The skill is presented as a Vue guidance and code-snippet toolbox, but it declares powerful capabilities including exec and write that are not necessary for static framework advice. This creates an unnecessary privilege surface where a broadly-triggered skill could execute shell commands or modify files during ordinary development assistance, increasing the risk of unintended or abusive actions.

Intent-Code Divergence

Medium

Confidence: 88% confidence
Finding: The documentation advertises operational behaviors such as create, query, export, import, save, and convert even though the skill content is fundamentally a static knowledge guide. These claims can mislead an agent into treating the skill as authorized for state-changing actions, expanding behavior beyond its legitimate scope and increasing the chance of unsafe file or workflow manipulation.

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The activation description is broad enough to match generic coding, debugging, testing, and deployment requests, not just Vue 3 Composition API guidance. Overbroad routing increases the chance this skill is invoked in contexts where its exec/write permissions and misleading operational claims could influence actions outside its intended domain.

Vague Triggers

Medium

Confidence: 85% confidence
Finding: The capability coverage line includes vague trigger keywords like 'Agent', '开发者', '代码生成', '调试测试', and '开发部署', which are generic enough to match many unrelated requests. In combination with privileged tools, these loose triggers make accidental or excessive activation more dangerous because the skill may be selected in situations far beyond Vue advice.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill declares exec-enabled and file-impacting operations but provides no prominent warning, consent requirement, or safety guidance for commands and save/export behavior. Users and agents may assume the skill is read-only educational content, which makes any hidden ability to alter the system or project unexpectedly risky.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.