Nm Conserve Code Quality Principles

• Outcome: Pass
• Latest audit: Jun 7, 2026 at 9:44 PM UTC
• Version:
  1.0.3

Overview

This is a code-quality guidance skill with no executable payload, credential use, persistence, or hidden behavior.

Install if you want general clean-code review guidance. Be aware it may trigger on broad architecture or design discussions, so users who prefer narrower activation should adjust the trigger phrases before use.

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: 82% confidence
• Finding: The trigger list contains broad terms such as `design`, `principles`, `architecture`, and `clean-code`, which can cause the skill to activate in many unrelated contexts. Over-broad activation increases the chance that the skill injects guidance unexpectedly, creating prompt-surface expansion and making it easier for an attacker to steer agent behavior via ambiguous or incidental language.

VirusTotal

65/65 vendors flagged this skill as clean.