Nm Pensive Tiered Audit

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:39 PM UTC
• Version:
  1.0.2

Overview

This markdown-only skill guides a tiered code audit and is purpose-aligned, with broad triggers as the main usability caution.

Install this if you want an agent to run a structured repository audit. Be aware that generic words like audit or review may invoke it, and it may read repository history and source files and create local .coordination findings files.

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: 95% confidence
• Finding: The trigger list includes broad, common terms like 'audit', 'review', and 'code-quality', which can cause the skill to activate in situations beyond the author's intended scope. In an agent environment, unintended invocation can steer workflows into this skill unexpectedly, increasing the chance of inappropriate file access, git command execution, or interference with other review tools.

VirusTotal

65/65 vendors flagged this skill as clean.