ClawHub
Back to skill

Security audit

通用文本一键转公众号推文工具

Security checks across malware telemetry and agentic risk

Overview

This is a WeChat article-formatting skill with a disclosed local save step and no executable code or hidden data transfer.

Install if you want a formatter that turns supplied text into WeChat-style articles. Before using it with private chats, meeting notes, or unpublished drafts, tell the agent whether to save the result, choose a non-sensitive output path, and review the generated content before publishing.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

High
Confidence
93% confidence
Finding
The trigger conditions are extremely broad, allowing the skill to activate on essentially any long-form or informal text input. In an agent environment, this can cause unintended invocation on sensitive user content, leading to unnecessary processing or downstream actions such as file creation without clear user intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill specifies automatic saving to a filesystem path by default, but does not require user confirmation or warn that content will be written to disk. This creates a risk of silently persisting sensitive drafts, chat logs, meeting notes, or market commentary to local storage, which may expose confidential information or create unexpected side effects.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.