ClawHub
Back to skill

Security audit

1-Click WOA

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it uses user-provided WeChat credentials, article text, and images to create WeChat Official Account drafts, with a disclosed local HTML fallback.

Install only if you are comfortable storing a WeChat AppSecret in the documented local credentials file and sending unpublished article text and selected images to WeChat APIs. Review the image_dir contents before running, confirm before creating drafts, and treat any generated article_fallback.html as sensitive unpublished content.

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
91% confidence
Finding
The skill explicitly instructs the agent to read a local credentials file, write fallback HTML files, and perform network requests to WeChat APIs, yet it declares no permissions. This creates a capability/permission mismatch that can mislead users and policy enforcement, increasing the risk of unexpected access to secrets and filesystem data during execution.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.