ClawHub
Back to skill

Security audit

微信公众号文章发布工具

Security checks across malware telemetry and agentic risk

Overview

This skill fits its WeChat article-writing purpose, but it also gives an agent authority to publish externally and handle secrets with insufficient final user-control safeguards.

Review before installing. Only use this with a WeChat account you are comfortable delegating to an agent, require a manual final approval before any publish or preview submission, and store credentials in protected environment configuration. Do not run the credential-check commands as written if they print API keys into logs or chat.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly enables direct publication to a public WeChat Official Account, which is an externally visible action with reputational and operational consequences. Because the description and usage guidance do not prominently warn that user-controlled Markdown will be transformed and published outward, an agent or user may trigger unintended publication of unreviewed, misleading, or sensitive content.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill requires `WECHAT_APP_ID` and `WECHAT_APP_SECRET`, which are sensitive credentials, but it does not include user-facing guidance on secure storage, least-privilege handling, or avoiding exposure in logs and prompts. In an agent setting, missing secret-handling guidance increases the risk of accidental disclosure, unsafe injection into subprocesses, or misuse of credentials to publish unauthorized content.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.