Dual-Mode Reasoner

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.0

Overview

This is a text-only reasoning helper that may change response structure when invoked but does not run code, access data, or request permissions.

Install this if you want structured reasoning for decisions where risk level matters. Be aware that implicit invocation may make the assistant use the six-section format automatically; disable implicit invocation or call the skill explicitly if you prefer manual control. Do not treat the skill as domain expertise for legal, medical, financial, or other regulated decisions.

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: 89% confidence
• Finding: The default prompt is broadly phrased to apply whenever a user 'needs a disciplined protocol' rather than a narrowly scoped task, which can cause the skill to activate for many ordinary reasoning requests. Combined with implicit invocation, this increases the chance the skill will be selected unexpectedly and alter model behavior or output format outside clear user intent.

VirusTotal

64/64 vendors flagged this skill as clean.