ClawHub
Back to skill

Security audit

微信公众号 Markdown 发布助手

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed WeChat publishing helper, but users should be careful because it handles account credentials and can upload or publish content.

Install only if you intend to let the agent use your WeChat Official Account credentials. Keep AppSecret and token files private, confirm every upload or direct publication, and avoid using it with confidential drafts unless sending that content and its images to WeChat is acceptable.

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)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases include very broad language such as '帮我发微信' and '写公众号文章', which can match ordinary conversation and cause the skill to activate when the user did not clearly intend to publish content. In this skill, accidental activation is more dangerous because activation can lead to credential use, external transmission of article content and images, and potentially publishing to a public account.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill clearly states it will upload images and article content to WeChat APIs, but it does not give a prominent privacy warning about sending potentially sensitive text, images, metadata, and account-linked publishing actions to a third party. Users may unknowingly transmit confidential drafts or personal information, which is especially risky because all external image URLs are replaced by uploaded copies on WeChat infrastructure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:465