ClawHub
Back to skill

Security audit

近思录智慧

Security checks across malware telemetry and agentic risk

Overview

This is a philosophy and self-cultivation reference skill with broad advice scope but no code, credential use, network access, or hidden automation.

Installers should treat this as a cultural/philosophical reference and reflection aid. For legal, medical, financial, employment, compliance, safety, or crisis situations, use appropriate professional or specialized guidance rather than relying on this skill's moral or management framing alone.

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
82% confidence
Finding
The invocation guidance is very broad ('修身/治学/处世/管理') and lacks boundaries, exclusions, or escalation rules. That can cause the agent to over-apply this philosophical skill to sensitive situations such as mental health, legal, medical, HR, or high-stakes organizational decisions where domain-specific safeguards are needed.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.