ClawHub

Mercado Libre

Security checks across malware telemetry and agentic risk

Overview

This Mercado Libre skill is disclosed and purpose-aligned, but it gives an agent broad authenticated ability to change or delete marketplace data without clear confirmation guardrails.

Install only if you are comfortable giving Membrane delegated access to your Mercado Libre account. Before any write or delete action, require the agent to show the exact action or API request, affected records, method, endpoint, and body, and approve it explicitly. Prefer discovered Membrane actions over raw proxy requests, and revoke the Mercado Libre/Membrane connection when finished.

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
84% confidence
Finding
The skill advertises create, update, and delete record operations but provides no guidance to require user confirmation before destructive changes. In an agent setting, this increases the risk of unintended or overly broad modifications to marketplace data because the model may interpret a vague user request as authorization to mutate or delete records.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The proxy request section enables arbitrary authenticated API calls, including write and delete operations, without warning about mutation risk, scope validation, or confirmation requirements. Because Membrane injects authentication automatically, an agent could directly perform sensitive actions against Mercado Libre with little friction, amplifying the impact of prompt mistakes or misuse.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal