screenshot-to-prototype

• Outcome: Pass
• Latest audit: May 29, 2026, 9:27 AM
• Version:
  1.0.0

Overview

This skill appears to be a straightforward screenshot-to-frontend-prototype helper, with some boilerplate documentation issues but no evidence of hidden, destructive, or data-exfiltrating behavior.

Reasonable to install if you want help turning UI screenshots into editable frontend code. Review generated code before using it, and be aware that the README's API_KEY and write-mode examples look like generic boilerplate rather than actual required behavior.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 77% confidence
• Finding: Using a placeholder trigger condition instead of a concrete invocation scope can cause the skill to be activated in unintended contexts. For a screenshot-to-prototype skill, vague scope increases the chance that an agent applies it to unrelated or sensitive inputs, which can lead to overbroad processing, accidental data exposure, or unsafe downstream actions based on misclassification.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: Documenting a write mode without clearly warning that it may modify files or user data can cause users or agents to invoke the skill with incorrect assumptions about safety. In an agentic environment, ambiguous write behavior is dangerous because it can lead to unintended file changes, overwrites, or persistence of generated content without informed consent or adequate review.

VirusTotal

66/66 vendors flagged this skill as clean.