Nm Leyline Evaluation Framework

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:38 PM UTC
• Version:
  1.0.2

Overview

This is a documentation-only evaluation framework with broad activation triggers and some high-impact automation examples, but no executable behavior or hidden access.

Install only if you want a general-purpose evaluation and scoring methodology. Be aware it may appear for broad evaluation-related requests, and do not turn its auto-merge, deployment, or rejection examples into real automation without explicit authorization, human review gates, audit logging, rollback plans, and environment-specific safeguards.

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: 84% confidence
• Finding: The trigger list contains very generic terms like `evaluation`, `scoring`, `metrics`, and `quality`, which can cause the skill to activate in many unrelated contexts. In agent systems, unintended activation can inject irrelevant workflow guidance into sensitive tasks, increasing the risk of confused-deputy behavior, bad decisions, or interference with more appropriate skills.

VirusTotal

64/64 vendors flagged this skill as clean.