ClawHub
Back to skill

Security audit

待办清单生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill only generates Markdown todo lists and requests no permissions; the main caveat is a broad trigger that could activate unintentionally.

This appears safe to install for generating Markdown todo lists. Be aware that the short Chinese trigger for "todo" may activate the skill in more situations than intended; using the explicit command or a more specific trigger would be cleaner.

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)

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
94% confidence
Finding
The trigger list includes the very short generic term '待办', which can match a wide range of unrelated user inputs and cause the skill to activate unexpectedly. This is not directly exploitable as code execution, but it can lead to unintended routing, prompt interference with other skills, or incorrect task generation in contexts where the user did not explicitly request this skill.

Static analysis

No suspicious patterns detected.