ClawHub
Back to skill

Security audit

Wechat Article Writer V2

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed WeChat article-formatting guide with no executable code, credential handling, or hidden data movement.

Install this if you want a WeChat Official Account Markdown layout workflow. Before use, confirm where generated .md files will be written and avoid overwriting existing files unless you explicitly intend to.

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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill metadata uses broad tags and trigger phrases such as general article-writing and structured content terms, which can cause the agent to invoke this skill for ordinary writing requests outside its intended WeChat-publication niche. Over-broad activation increases the chance of unintended instruction capture, causing the model to follow this skill’s rigid workflow when a simpler or different skill would be more appropriate.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The main invocation instruction says to use the skill whenever the user needs to write a WeChat article, but it does not define boundaries, exclusions, or confirmation requirements. This can lead to over-activation and prompt hijacking of normal writing tasks, especially when the user only wants content help rather than the full markdown-module workflow.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill instructs the agent to save the final output as a `.md` file to a user-specified directory or the current working directory, but it does not require explicit user confirmation or safe handling for overwrites. In an agent environment with file-system tools, this creates a risk of unintended file creation, clobbering existing files, or writing sensitive content to an unexpected location.

Static analysis

No suspicious patterns detected.