Cognitive Skill Factory

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:35 PM UTC
• Version:
  2.0.1

Overview

This skill is a disclosed decision-framework bundle with an optional installer, and I found no hidden data access, exfiltration, or destructive behavior.

Safe to install as an advisory thinking-framework skill. Before running scripts/install-all.sh, review the additional skills it installs because they will persist in your agent environment. Also verify the license with the publisher before modifying, redistributing, or using it commercially because the artifacts conflict between MIT and proprietary terms.

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: 88% confidence
• Finding: The manifest description uses broad promotional language about decision-making and top-tier thinkers without defining concrete activation boundaries, allowed tasks, or disallowed domains. In an agent setting, vague scope increases the chance of over-invocation and users applying the skill to sensitive decisions beyond its intended competence, which can lead to unsafe or misleading guidance.

VirusTotal

64/64 vendors flagged this skill as clean.