Mercado Pago

• Outcome: Review
• Latest audit: May 29, 2026 at 9:38 PM UTC
• Version:
  1.0.1

Overview

This Mercado Pago skill is purpose-aligned, but it needs Review because it gives broad authenticated payment-account control without clear confirmation guardrails for changes.

Install only if you trust Membrane and the npm CLI source. Connect only the intended Mercado Pago account, review any consent scopes, prefer pre-built actions over raw proxy calls, and require the agent to ask before any payment, refund, POST, PUT, PATCH, DELETE, or account-changing operation.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill documents a generic proxy request capability that supports mutating HTTP methods like POST, PUT, PATCH, and DELETE without any guardrails, confirmation requirements, or warnings about side effects. In a payments context, this increases the risk of accidental or overly broad data-changing actions such as refunds, order updates, or other financial state changes being executed from ambiguous user requests.

VirusTotal

63/63 vendors flagged this skill as clean.