ClawHub
Back to skill

Security audit

业务模块工程师 模块开发

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only skill for WelineFramework business-module development, with no hidden code, install hooks, credential access, or persistence.

Install this if you want help with WelineFramework module-local development. Before use, confirm the target module and review any proposed code edits and setup command output, especially outside disposable development environments.

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
87% confidence
Finding
The invocation guidance uses broad terms like module development, controller, menu, register, setup, feature module, and backend page, which overlap with common software tasks and can cause this skill to activate outside its intended boundary. In an agentic system, ambiguous activation increases the chance of misrouting work to a higher-privilege or unsuitable skill, potentially leading to unintended code changes or bypass of more specialized review paths.

Static analysis

No suspicious patterns detected.