Nm Archetypes Architecture Paradigm Client Server

• Outcome: Pass
• Latest audit: Jun 7, 2026 at 9:44 PM UTC
• Version:
  1.8.6

Overview

This appears to be a benign advisory skill whose main issue is broad activation wording, not malicious behavior.

Reasonable to install if you want architecture or distributed-systems guidance. Expect possible over-activation from broad trigger phrases; invoke it explicitly for relevant design or trust-boundary work and disable or narrow it if it interferes with unrelated tasks.

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: 96% confidence
• Finding: The trigger list includes broad phrases such as "architecture," "distributed-systems," and "trust boundaries," which are likely to activate the skill in many unrelated contexts. Overbroad auto-activation can cause the wrong skill to influence agent behavior, leading to scope confusion, lower-quality guidance, and increased exposure to prompt-injection or unsafe instruction blending from unintended contexts.

VirusTotal

64/64 vendors flagged this skill as clean.