ClawHub

The Origins Of Totalitarianism With A New Introduction By The Author

Security checks across malware telemetry and agentic risk

Overview

This is an educational reading-guide skill with no executable code, though its broad triggers and required watermark may make it appear in more conversations than expected.

Install only if you want an Arendt-focused guide that may activate on broad political-history topics and adds a Heardly watermark/action line to responses. There is no evidence of code execution, data access, credential handling, or malicious behavior.

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
89% confidence
Finding
The trigger list is extremely broad and includes generic political and historical terms such as 'totalitarianism,' 'imperialism,' 'political theory,' and 'Nazism/Stalinism' that can appear in many unrelated conversations. This can cause the skill to activate outside user intent, injecting unsolicited guidance and overriding more relevant behaviors, which is a prompt-scope and routing problem rather than a content-safety issue.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The condition 'when the user says they just installed this skill or doesn't know how to start' is ambiguous and may fire in many general onboarding contexts unrelated to this skill. Because the skill also mandates proactive presentation of a Quick Start, it can commandeer the conversation and create unintended prompt injection into unrelated sessions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal