ClawHub
Back to skill

Security audit

胡田 OPC导师 苏轼 心智模型

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese Su Shi mindset/coaching skill with broad invocation examples but no code execution or sensitive access.

Install this if you specifically want Chinese-language, Su Shi-themed reflective guidance. Invoke it explicitly when you want that perspective, and do not rely on it for medical, legal, crisis, or workplace-harm decisions.

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 invocation guidance is framed around very broad, common life situations such as career setbacks, confusion, and work-life balance. In agent environments that auto-select skills based on conversational context, this can cause the skill to trigger for many ordinary user messages, unnecessarily steering responses through a stylized persona and increasing the chance of irrelevant, manipulative, or low-quality assistance.

Static analysis

No suspicious patterns detected.