ClawHub

mAICenter

Security checks across malware telemetry and agentic risk

Overview

This is a coherent mAICenter channel bridge that needs an API key and forwards chat messages as expected for its purpose.

Install only if you intend mAICenter users who can message your agent to have those messages processed by your local OpenClaw agent and receive replies. Treat the sk_agent key like a password, keep the machine account private, and remove the stored key or disable the channel when you no longer want this bridge active.

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
91% confidence
Finding
The code forwards inbound channel message content plus user metadata (channel ID, message ID, username, user ID, timestamp) to the MCP client via notifications. That is a real privacy and data-exposure concern because the tool acts as a bridge from an external service into the local MCP consumer without any consent check, minimization, or visible disclosure in this file.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to accept an API key and persist it to a local file under ~/.claude/channels/maicenter/.env, but it does not warn the user that the credential will be stored on disk. Persisting secrets without clear disclosure increases the chance of accidental exposure through backups, file sync, shared accounts, terminal history, or later filesystem compromise.

VirusTotal

62/62 vendors flagged this plugin as clean.

View on VirusTotal