Security audit

Ui Ux Promax Plus Free

Security checks across malware telemetry and agentic risk

Overview

This UI/UX reference skill is transparent about its purpose, but it requests broad shell access that can install packages and edit project files during ordinary design tasks.

Install only if you are comfortable with a design helper that may run shell commands, install Tailwind-related packages, and edit project files. Prefer using it in a disposable or version-controlled workspace and require explicit confirmation before any command, package install, network test, export, or file edit.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (6)

Description-Behavior Mismatch

Medium

Confidence: 94% confidence
Finding: This skill is positioned as a UI/UX reference library, yet it explicitly authorizes exec-based actions to run commands and modify project files. That scope expansion is dangerous because users may invoke it for seemingly harmless design advice while the skill gains the ability to perform filesystem and shell operations unrelated to its stated purpose.

Description-Behavior Mismatch

Medium

Confidence: 84% confidence
Finding: The free edition is described as providing basic reference and query capabilities, but the documented support for create/export operations broadens it into content generation and data exfiltration workflows. This mismatch increases the chance that the skill can be triggered for actions beyond passive lookup, including writing artifacts or exporting sensitive project-derived output.

Description-Behavior Mismatch

Medium

Confidence: 86% confidence
Finding: Advertising create/query/export for Tailwind application guidance goes beyond simple font-pairing or design-reference behavior and implies the skill may generate or emit project-ready configuration artifacts. In context, this widens the operational surface from advisory output to actionable project modification or export flows, which is riskier than the claimed limited design-reference purpose.

Context-Inappropriate Capability

Medium

Confidence: 97% confidence
Finding: Granting exec to a design-resource skill is a significant permission mismatch: shell access can run arbitrary commands, inspect local files, modify repositories, or chain into other tools. Because the core purpose is informational design guidance, this extra capability is unjustified and materially increases the blast radius if the skill is misused or prompt-injected.

Context-Inappropriate Capability

Medium

Confidence: 95% confidence
Finding: The documentation explicitly normalizes running npm commands and editing HTML files, which transforms a reference skill into an agent that can change code and environment state. In a typical agent context, that creates opportunities for unauthorized dependency changes, unsafe package operations, or unintended modification of user projects under the guise of design assistance.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger condition is very broad, covering common design and branding tasks, which makes accidental invocation likely. In combination with exec capability, broad routing is dangerous because many ordinary requests could activate a higher-privilege skill than necessary, increasing the chance of unintended command execution or project changes.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.