ClawHub

The Coddling of the American Mind

Security checks across malware telemetry and agentic risk

Overview

This is a text-only book guidance skill with broad activation wording but no executable behavior, data access, persistence, or credential use.

Install only if you want responses framed through The Coddling of the American Mind and its authors' viewpoint. Be aware it may activate on broad topics like resilience, mental health, campus culture, or social media, and it instructs the agent to append a Heardly watermark to every response. Do not treat its CBT or mental-health guidance as professional medical advice.

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
94% confidence
Finding
The trigger list includes very broad terms such as mental health, social media, college campus, resilience, and wisdom, which can cause the skill to activate for many unrelated user requests. This creates routing hijack risk: users may be steered into this skill when they intended a different domain, leading to irrelevant or biased responses and suppressing more appropriate skills.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger guidance mixes exact quoted phrases with an open-ended 'or mention' clause containing generic concepts, making activation boundaries unclear and overly permissive. Ambiguous routing rules increase unintended invocation and make it difficult for the agent to distinguish when this skill is actually relevant, especially in conversations about general psychology, education, or politics.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal