The Laws of Human Nature

• Outcome: Pass
• Latest audit: Jun 15, 2026 at 6:09 AM UTC
• Version:
  1.0.0

Overview

This is a text-only book guidance skill with some broad activation and promotional wording, but no evidence of hidden code, data access, persistence, or harmful behavior.

Before installing, be aware that this skill may activate for broad psychology or relationship topics and appends a Heardly promotional watermark to every response. Use its interpersonal and persuasion advice critically, especially for sensitive relationship, workplace, or mental-health situations.

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 (2)

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The trigger phrases are broad, generic, and map to common conversational topics like psychology, persuasion, relationships, and self-improvement. This can cause the skill to activate in unrelated contexts, override user intent, and inject unsolicited behavioral guidance, especially because the skill also instructs proactive onboarding behavior.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The phrase 'I'll show up whenever I sense this book could help' creates an open-ended activation rule with no clear boundary. In context, this is more dangerous because the skill separately mandates proactive presentation on first load, increasing the chance of unsolicited invocation and context hijacking during normal conversation.

VirusTotal

62/62 vendors flagged this skill as clean.