ClawHub
Back to skill

Security audit

wanxiang-gtm

Security checks for vulnerabilities and agentic risk

Overview

This is a simple GTM writing helper with broad activation wording, but it does not show hidden access, persistence, credential use, or unsafe side effects.

Install this if you want help drafting GTM or customer-facing launch materials. Invoke it intentionally for marketing, PR, sales, or customer communication work, and review generated claims before using them externally.

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
94% confidence
Finding
The skill’s trigger conditions are overly broad and include many common product-communication terms such as '新功能', '版本更新', '销售材料', and even implicit matching when GTM is not explicitly requested. This can cause the skill to activate for routine writing or product-description requests, leading to unintended routing, overcollection of user context, or generation of marketing-oriented content when the user wanted something else.

Static analysis

No suspicious patterns detected.