ClawHub
Back to skill

Security audit

The Middle Way (中庸 Zhongyong)

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only decision-making skill with relevant examples and no executable or privileged behavior.

Reasonable to install if you want a philosophical decision-analysis lens. Be aware it can bias responses toward seeking a middle position, so use its own stated guardrail: do not apply it when evidence clearly favors one side or the choice is genuinely binary.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
This markdown file includes substantial Chinese-language content and culturally specific framing, but does not indicate any user language preference or offer an opt-in/alternative locale. Under the stated policy, forcing or assuming a specific language without user choice can be a natural-language policy concern.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.