wordcloud-skill

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:24 PM UTC
• Version:
  1.0.1

Overview

This is a straightforward local word-cloud generator with disclosed file input and image output behavior.

Install dependencies from a trusted Python environment, point the skill only at the specific text or Markdown folder you want analyzed, choose the output directory deliberately, and review stopwords.md if excluded words should not persist across future runs.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (2)

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The trigger guidance is broad enough that the skill may be invoked whenever a user wants to 'visualize text in a different way,' even if they did not request file processing or output generation. Overbroad routing increases the chance of unintended execution, which is risky here because the skill can read files/directories and write image output or modify stopword data.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The documentation notes that the skill may write image files and instructs modification of stopwords.md, but the description does not clearly warn users that it performs filesystem writes and persistent changes. Hidden or insufficiently disclosed write behavior can surprise users, overwrite data, or create integrity issues in the skill's environment.

VirusTotal

66/66 vendors flagged this skill as clean.