ClawHub

文颜

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward WeChat publishing guide with expected but sensitive use of an external CLI, image uploads, and WeChat credentials.

Before installing, verify the npm package and consider pinning a known version. Review the Markdown file, frontmatter, cover image, embedded image paths, and target WeChat account before publishing. Keep WECHAT_APP_SECRET, WECHAT_APP_ID, and any server API key out of source control, logs, screenshots, and shared shells.

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
85% confidence
Finding
The guide states that the CLI will automatically upload images in the article to WeChat's media library, but it does not clearly warn users that local files will be transmitted to a remote service. In a publishing tool, network upload is expected, but the lack of explicit disclosure increases the risk of accidental exfiltration of sensitive local images or unintended publication of private content.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The documentation instructs users to place WeChat application credentials in environment variables but provides no guidance on protecting, scoping, or avoiding exposure of those secrets. While environment variables are a common mechanism, users may inadvertently leak them via shell history, logs, CI output, or shared environments if safe handling is not documented.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal