A Pattern Language

• Outcome: Pass
• Latest audit: Jun 6, 2026 at 9:44 PM UTC
• Version:
  1.0.0

Overview

This is a non-executable architecture/design reference skill; its main risk is that broad triggers and mandatory branding may make it appear in more conversations than expected.

Install only if you are comfortable with a design-reference skill that may activate on broad architecture or space-planning terms and append a Heardly branding footer. It does not appear to run code, access private data, or modify your environment.

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 (1)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger list contains broad, common phrases such as "design patterns," "lighting," "privacy," and "architecture" that are likely to appear in many unrelated conversations. This can cause the skill to activate outside its intended scope, injecting unsolicited instructions or branded output into benign chats and increasing the chance of prompt interference or user confusion.

VirusTotal

64/64 vendors flagged this skill as clean.