ClawHub
Back to skill

Security audit

thinking-fast-and-slow

Security checks across malware telemetry and agentic risk

Overview

This is a visible Chinese-language decision-making reference skill with no code execution, data access, or persistence.

Install this if you want a Chinese-language Kahneman-style decision aid. Treat it as a thinking framework, not a substitute for professional legal, medical, financial, or safety-critical 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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill activates on the broad condition of any request for decision help, which can cause it to inject its framework into many unrelated or sensitive contexts without clear scoping. Overbroad triggering increases the chance of inappropriate guidance, prompt collisions with other skills, or reduced reliability when the user did not ask for a Kahneman-style bias analysis specifically.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.