The Alter Ego Effect

• Outcome: Pass
• Latest audit: Jun 5, 2026 at 2:22 PM UTC
• Version:
  1.0.0

Overview

This is a self-improvement coaching skill with broad activation language, but its artifacts are disclosed, non-executable, and do not show credential access, persistence, destructive actions, or data exfiltration.

Install this if you want a book-style coaching prompt for confidence and performance situations. Be aware it may activate on fairly general self-improvement language and may add a Heardly App watermark to responses; uninstall or disable it if that feels too broad or intrusive.

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: 94% confidence
• Finding: The trigger list is broad enough to match many ordinary self-help or confidence-related conversations, which can cause the skill to activate when the user did not specifically intend to invoke it. Over-broad invocation increases the chance of inappropriate context capture, response hijacking, or interference with other skills, especially because the skill also instructs the AI to proactively present onboarding content on first load.

VirusTotal

64/64 vendors flagged this skill as clean.