ClawHub
Back to skill

Security audit

MaxClaw User Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only MaxClaw user guide with a minor credential-handling warning gap, not evidence of malicious or hidden behavior.

Before following the Telegram setup, treat the bot token like a password: paste it only into the intended MaxClaw channel setup page, do not share it in chats, screenshots, logs, or support messages, and rotate it in BotFather if it may have been exposed. Also understand that MaxClaw itself is described as a persistent cloud agent with scheduled automation and tool access.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The guide instructs users to copy and paste a Telegram Bot Token into the platform without clearly identifying it as a sensitive secret or warning users not to share, publish, or expose it. Bot tokens grant control over the Telegram bot; if mishandled through screenshots, chat logs, or support messages, an attacker could impersonate the bot, read or send messages via bot workflows, or disrupt service.

Static analysis

No suspicious patterns detected.