ClawHub

微信自动写作排版专业技能（包含公众号发布功能）

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only WeChat writing and publishing skill with disclosed public-posting capabilities, so it is benign but should be used with care around account credentials and publication approval.

Install as a writing/publishing reference if you intend to manage a WeChat public account. Only provide real WeChat credentials in a controlled environment, keep draft creation as the default, preview the article and images, and require explicit human approval before any publish_draft, publish_now, or full_auto_publish action.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README documents a workflow that culminates in creating drafts and submitting articles for publication to a live WeChat public account, but it does not prominently warn that these operations can modify external account content and may trigger irreversible posting actions. In an agent skill context, this omission increases the risk that an autonomous or semi-autonomous agent could perform real-world publishing actions without explicit user confirmation or adequate safeguards.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill enables direct public posting and even advertises one-click publishing, but it does not present a prominent user-facing warning, confirmation gate, or approval requirement before irreversible publication. In an agent setting, this increases the risk of accidental or unauthorized public posting of unreviewed, harmful, or brand-damaging content.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal