ClawHub
Back to skill

Security audit

WeChat Article to Markdown

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed WeChat article-to-Markdown converter whose network, script execution, and local file writes fit its stated purpose.

Install only if you are comfortable running a Python scraper that fetches article pages and may download remote images. Use trusted WeChat URLs, choose a dedicated output directory to avoid overwriting files, and consider running it in a sandbox for untrusted or high-volume conversions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to install packages, execute a Python script, fetch remote content from WeChat, and write Markdown and image files, but it does not declare any permissions for network, shell, or file-write behavior. This mismatch is dangerous because a caller or reviewer may treat the skill as lower-privilege than it really is, reducing oversight around package installation, outbound requests, and filesystem changes.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal