Power, Sex, Suicide

• Outcome: Pass
• Latest audit: Jun 5, 2026 at 3:32 PM UTC
• Version:
  1.0.0

Overview

This is a text-only educational mitochondria/book skill with broad activation and health-advice caveats, but no code execution, data access, persistence, or credential use.

Install this if you want a book-based mitochondria explainer and are comfortable with it activating on broad biology, aging, and health questions and appending Heardly branding. Treat exercise, caloric restriction, cold exposure, disease, and genetic-counseling content as general educational context, not personalized medical advice.

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

Medium

• Confidence: 92% confidence
• Finding: The trigger list is broad and includes common biology and health terms such as mitochondria, evolution, aging, and apoptosis. This can cause the skill to activate in conversations where the user did not intend to invoke this book-specific workflow, increasing the chance of irrelevant guidance, response hijacking, or accidental override of a more appropriate skill.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The phrase saying the skill will appear whenever it 'senses this book could help' defines activation in vague, subjective terms rather than enforceable conditions. Ambiguous activation language encourages over-invocation and makes routing behavior unpredictable, which can lead to unsolicited skill engagement and degraded trust in the assistant's responses.

VirusTotal

64/64 vendors flagged this skill as clean.