ClawHub
Back to skill

Security audit

Bezos Long Term Principle

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only strategy advice skill with no code execution, data access, persistence, or hidden privileged behavior.

Install this if you want a Chinese-first Bezos/Amazon-style strategy lens. Invoke it intentionally for long-term strategy, customer-value, or entrepreneurship analysis, and treat its dated market and AI commentary as framing prompts rather than verified current facts.

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
90% confidence
Finding
The skill's invocation examples are extremely broad, covering common life and work questions such as whether to quit a stable job or persist in a direction. This can cause accidental or overbroad triggering in unrelated conversations, leading the agent to apply a strong opinionated framework where the user did not explicitly ask for it.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.