ClawHub
Back to skill

Security audit

Wechat To Obsidian

Security checks across malware telemetry and agentic risk

Overview

This skill clearly aims to save user-requested WeChat articles into an Obsidian vault, with local file creation and image downloads disclosed as part of that purpose.

Before installing or using it, confirm the Obsidian vault or output folder and remember that it will fetch remote WeChat content, create a Markdown note, and may download article images into an images subdirectory. The package as submitted appears incomplete because only SKILL.md is present, so the referenced script and config files would need to be supplied for it to work.

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 (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs the agent to write Markdown files into the user's local Obsidian vault and download remote images into a local images/ directory, but the top-level description does not clearly warn that local filesystem writes and network-driven file downloads will occur. This can cause users to trigger local persistence of untrusted remote content without informed consent, increasing the risk of unwanted file creation, storage of malicious or inappropriate content, or accidental writes into sensitive note locations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.