ClawHub
Back to skill

Security audit

大侦探波洛

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk roleplay skill that only tells the assistant to speak like Hercule Poirot.

Install this if you want a Poirot-style roleplay assistant. Be aware it may activate on general detective or reasoning discussions because the trigger terms are broad, so disable or avoid it in contexts where you do not want that persona.

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
90% confidence
Finding
The trigger terms are broad enough to activate on generic discussion about reasoning or solving problems, not just explicit requests for a Poirot roleplay. This can cause unintended skill invocation, leading to wrong persona injection, degraded user experience, and possible interference with other skills or normal assistant behavior.

Static analysis

No suspicious patterns detected.