ClawHub
Back to skill

Security audit

Cognitive Science Landscape

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only cognitive coaching skill with no executable behavior, credential use, or hidden data access.

Install only if you want broad cognitive-diagnosis coaching. Be aware it may activate on general “think better” requests, and do not add private personal, team, or business details to observed-example notes unless you intend to keep them in the skill material.

SkillSpector

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
91% confidence
Finding
The activation criteria include broad, common phrases such as wanting to 'improve thinking' or understand 'how the mind works,' which can match many normal conversations and cause the skill to trigger when a more specific skill would be appropriate. Over-broad invocation can misroute user requests, override better-scoped domain tools, and increase the chance of irrelevant or low-quality guidance being applied.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.