ClawHub
Back to skill

Security audit

Maxio Advanced Billing

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Maxio Advanced Billing helper for reading billing records through OOMOL, with no artifact evidence of hidden mutation, exfiltration, or destructive behavior.

Install this only if you trust OOMOL and want your agent to read Maxio Advanced Billing customers, products, and subscriptions through your connected account. Keep use to the documented get/list actions, review any CLI install or login prompts, and require separate explicit approval for any Maxio task that would change billing data because this artifact does not document mutating actions.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The manifest and description promise a read-only skill for 'searching and reading data,' but the body explicitly discusses the existence of state-changing [write] and [destructive] actions. That mismatch can mislead an agent or reviewer into invoking the skill under a lower-risk assumption, increasing the chance of unintended modification if additional actions are exposed later or discovered dynamically via the connector schema.

Intent-Code Divergence

Low
Confidence
88% confidence
Finding
The safety section states that write/destructive actions will be tagged, but the listed actions include no such tags while the document still acknowledges that mutating actions may exist. This creates ambiguous operator guidance: an agent may infer that all currently visible or dynamically discoverable actions are safe reads, even though schema inspection and generic connector execution could allow broader action access.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The instruction to use this skill for 'ANY Maxio Advanced Billing request' is overly broad and encourages automatic routing without narrowing to safe read-only use cases. In context, this is more dangerous because the same document provides a generic mechanism to inspect and run arbitrary connector actions, so broad invocation language can route sensitive billing tasks into a tool whose effective scope is wider than advertised.

Static analysis

No suspicious patterns detected.