The Dictators Handbook

Security checks across malware telemetry and agentic risk

Overview

This appears to be an instruction-only political analysis skill with a broad activation scope but no evidence of harmful code, credentials use, persistence, or data access.

Reasonable to install if you want political-incentive or selectorate-style analysis. Be aware it may activate on broad politics terms such as democracy, autocracy, or corruption, so disable or narrow it if you only want it for explicit references to the book or framework.

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
90% confidence
Finding
The skill declares triggers on very broad political terms such as autocracy, democracy, corruption, and institutional design, plus an onboarding rule that may activate when a user merely says they just installed the skill or do not know how to start. This can cause over-invocation in unrelated conversations, leading the assistant to steer discussion into this skill unexpectedly and override user intent or crowd out more appropriate skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal