ClawHub
Back to skill

Security audit

Daily Wechat Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill matches a WeChat writing workflow, but it overstates its automation and can use WeChat credentials to create drafts and fetch arbitrary image URLs.

Review this carefully before installing. Use test WeChat credentials first, do not connect a production account until the author clarifies which parts are mock versus real, and avoid feeding markdown with untrusted remote image URLs until URL-fetch safeguards and explicit upload confirmation are added.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill description advertises automatic collection from multiple external platforms and automatic upload to WeChat, but it does not clearly warn the user about ongoing third-party data transfers, scheduled execution, or what content may be sent off-platform. This creates a real transparency and consent issue: users may enable the skill without understanding that it performs recurring external fetches and publishes generated output to another service.

Static analysis

No suspicious patterns detected.