Nm Abstract Escalation Governance

• Outcome: Pass
• Latest audit: Jun 7, 2026 at 10:42 PM UTC
• Version:
  1.8.6

Overview

This is a documentation-only skill for deciding when to use stronger models, with no code execution or data access.

Safe to install if you want model-escalation guidance. Be aware it may appear in broader agent or governance discussions, so treat its advice as optional guidance rather than an automatic decision rule.

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: 79% confidence
• Finding: The trigger list includes broad terms like `agents`, `governance`, and `orchestration`, which can cause the skill to activate in unrelated contexts. Over-broad invocation increases prompt-surface exposure and may inject escalation-governance instructions into conversations where they were not intended, potentially interfering with safer or more specific task handling.

VirusTotal

64/64 vendors flagged this skill as clean.