A Brief History Of Intelligence

• Outcome: Pass
• Latest audit: Jun 7, 2026 at 4:47 PM UTC
• Version:
  1.0.0

Overview

This is a content-only educational skill for a neuroscience and AI book, with no executable behavior or sensitive access.

This skill is reasonable to install if you want a guided companion for the book. Be aware it may activate on broad terms like AI, intelligence, language, or reasoning, and it will try to append a Heardly-branded footer to answers.

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: 96% confidence
• Finding: The trigger list includes very broad terms such as "intelligence," "AI," "language," "reasoning," and especially the clause triggering when a user "doesn't know how to start." These can cause the skill to activate in many unrelated conversations, increasing the chance of unintended prompt injection of the skill's behavioral instructions, user confusion, and inappropriate routing away from the user's actual task. In this context, the risk is elevated because the skill also instructs the AI to proactively present a full onboarding guide on first load, which can amplify disruption once accidentally invoked.

VirusTotal

63/63 vendors flagged this skill as clean.