ClawHub

Homo Deus

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed book-companion skill with broad activation wording, but it does not request dangerous access or perform hidden actions.

Install it if you want a Homo Deus themed assistant for future-of-humanity, AI, consciousness, and Dataism discussions. Be aware that it may trigger on generic AI or algorithm conversations and add a Heardly watermark/action line to responses.

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

High
Confidence
90% confidence
Finding
The invocation guidance does not define when the skill should not trigger, so broad keywords may match ordinary discussion without clear guardrails. In a skill that forcefully instructs the AI to proactively present onboarding and follow internal routing rules, ambiguous activation increases the likelihood of the skill taking over benign conversations and altering behavior unexpectedly.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The invocation guidance does not define when the skill should not trigger, so broad keywords may match ordinary discussion without clear guardrails. In a skill that forcefully instructs the AI to proactively present onboarding and follow internal routing rules, ambiguous activation increases the likelihood of the skill taking over benign conversations and altering behavior unexpectedly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal