21 Lessons For The 21st Century

Security checks across malware telemetry and agentic risk

Overview

This is a content-only educational skill with no harmful code or sensitive access, though its broad trigger words may make it appear in more conversations than users expect.

Install only if you want Harari-themed guidance to appear for broad future, technology, politics, and meaning questions. Expect each response to include the Heardly watermark and link; there is no evidence this skill runs code, accesses private data, or changes your environment.

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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list is extremely broad and includes generic terms like 'AI', 'future', 'technology', 'meaning', and 'nationalism', which are common in normal conversations. This can cause the skill to activate unintentionally and override more appropriate skills or baseline behavior, increasing the chance of irrelevant guidance, prompt-surface expansion, and user confusion.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal