ClawHub

Hotmart

Security checks across malware telemetry and agentic risk

Overview

This Hotmart integration is coherent, but it gives an agent broad authenticated access to business and financial account actions without enough explicit safety boundaries.

Install only if you trust Membrane with delegated Hotmart access. Use the least-privileged Hotmart account available, prefer read-only action discovery first, and require explicit confirmation before purchases, refunds, withdrawals, deletes, customer or subscription changes, sends, or any POST/PUT/PATCH/DELETE proxy request.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The invocation text is broad enough to trigger on many generic requests involving data management or automation, which can cause the agent to select this skill outside a clearly intended Hotmart-specific context. In a skill that can connect to external services and perform actions, over-broad routing increases the chance of unintended access, destructive operations, or data exposure through mis-invocation.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly documents a generic authenticated proxy mechanism for arbitrary API paths and methods, including POST, PUT, PATCH, and DELETE, but does not warn that these calls may modify or delete production data. Because the proxy automatically injects authentication, an agent could perform powerful state-changing operations against Hotmart with little friction and without prompting the user about risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal