RentaUnHumano MCP

• Outcome: Pass
• Latest audit: May 28, 2026 at 12:56 PM UTC
• Version:
  1.0.0

Overview

The skill is openly a paid external-service integration for hiring humans, with expected but significant real-world, payment, and data-sharing risks.

Install only if you are comfortable giving an agent access to an external service that can create paid real-world tasks and exchange operational details with human workers. Use sandbox mode first, review or pin the npm MCP server where possible, use a dedicated API key, and require explicit confirmation for paid, bulk, cancellation, review, dispute, or sensitive-location tasks.

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: 94% confidence
• Finding: The skill explicitly enables posting missions, sending messages, uploading proof, managing reviews/disputes, and handling payments through an external service and human workers, but it does not clearly warn that user-supplied data may be disclosed outside the local agent environment. In this context, task descriptions can contain addresses, business details, photos, contact information, and other sensitive operational data, making the omission materially risky rather than a harmless documentation gap.

VirusTotal

60/60 vendors flagged this skill as clean.