ClawHub
Back to skill

Security audit

Wolai MCP 技能

Security checks across malware telemetry and agentic risk

Overview

This is a real Wolai notes integration, but it gives unsafe instructions that could expose a powerful Wolai access token to the AI chat.

Install only if you intend to let the assistant operate your Wolai notes. Do not paste the Wolai MCP token into chat; configure it manually in the local environment or a secure credential store, rotate it if it may have been shared, and confirm destructive operations such as permanent deletes before running them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Intent-Code Divergence

Medium
Confidence
99% confidence
Finding
The credential precheck explicitly tells users to paste their Wolai token into the AI assistant, which directly contradicts the earlier guidance not to share the token in chat. This creates a real credential exposure path because chat messages may be logged, retained, or visible to systems beyond the user's local environment.

Missing User Warnings

High
Confidence
99% confidence
Finding
Suggesting that the user give a live API token directly to the AI assistant is unsafe because it normalizes secret sharing through the chat channel. In the context of a skill that can read, write, search, modify, and delete notes, compromise of this token can grant broad access to user data and destructive actions.

Ssd 3

High
Confidence
99% confidence
Finding
The precheck block encourages unsafe credential handling by offering token disclosure to the AI assistant as a setup path. Because this skill is designed to operate on the user's Wolai workspace over an authenticated remote API, leaked credentials could enable unauthorized reading, modification, deletion, or persistence of content.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.