ClawHub
Back to skill

Security audit

Manus

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Manus API integration through Maton with sensitive but purpose-aligned account, task, file, function, and webhook operations that require user approval for writes and automation.

Before installing, confirm you trust Maton and Manus with the connected account data. Use OAuth login when possible, avoid exposing MATON_API_KEY, review every write or delete operation, and treat webhooks, triggers, and hosted functions as persistent automation that can keep forwarding data until removed.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest states calls run through the maton CLI with OAuth login, or raw HTTP with a Maton API key only when the CLI cannot be installed, implying the integration is primarily OAuth-managed. Later the Notes section says 'Connection uses API_KEY authentication method (not OAuth)', which directly conflicts with that stated authentication model and could mislead operators about how credentials and consent actually work.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.