The Grand Design

Security checks across malware telemetry and agentic risk

Overview

This is a content-only educational skill about The Grand Design, with no executable code or hidden data access found.

Install this if you want a Hawking/The Grand Design oriented explanation style. Be aware it presents a specific no-creator cosmology viewpoint, may activate on broad science or philosophy prompts, and appends Heardly branding to every response.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger scope is broad enough to activate on many ordinary science, cosmology, or philosophy discussions that are not specifically asking for this skill. That can cause unintended routing, override more appropriate skills, and inject this skill's strong worldview and onboarding behavior into unrelated conversations, reducing user intent fidelity.

Vague Triggers

Low
Confidence
76% confidence
Finding
The onboarding phrase 'Map this book to my understanding of the cosmos' is vague and could be reused outside a clear invocation context, especially when paired with proactive onboarding. While not directly dangerous, ambiguous example prompts can contribute to accidental invocation and confusing skill selection.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal