Dollar Platoon | On-Demand Gigworkers

• Outcome: Review
• Latest audit: May 28, 2026 at 8:14 AM UTC
• Version:
  1.0.0

Overview

This is an instruction-only payroll marketplace skill, but its examples explicitly price paid social engagement, reviews, account creation, and spam-folder manipulation.

Install only after reviewing whether your intended use is lawful, consent-based task payroll. Avoid using this skill for fake engagement, review manipulation, account farming, spam evasion, or anything that violates another platform's rules, and treat wallet deposits, API keys, share tokens, approvals, and payout actions as sensitive financial operations.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Context-Inappropriate Capability

High

• Confidence: 99% confidence
• Finding: The recommended-prices section explicitly supports paid actions such as upvotes, follows, reviews, comments, account creation, and other coordinated engagement across third-party platforms. In context, this is not a neutral payroll abstraction: it operationalizes a marketplace for deceptive amplification, spam, fake engagement, and account farming at scale, which can directly facilitate platform abuse and influence operations.

Intent-Code Divergence

Medium

• Confidence: 96% confidence
• Finding: The document states that illegal and abusive uses are prohibited, but elsewhere provides detailed task categories and pricing that materially enable deceptive or suspicious conduct. This contradiction weakens safeguards, signals lax enforcement, and can be read as policy theater rather than an effective security or abuse-prevention control.

Vague Triggers

Medium

• Confidence: 83% confidence
• Finding: The trigger phrases are broad enough that the skill could activate in common conversations about payroll, pricing, reputation systems, or generic 'how it works' requests. Overbroad invocation increases the chance the agent surfaces high-risk financial or abuse-enabling guidance outside the user's intended context.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The top-level description promotes wallet management, payouts, public submission links, and integrations without equally prominent warnings about irreversible deposits, auto-approval behavior, third-party task risk, and custodial hot-wallet exposure. This can mislead users into engaging with financially irreversible or abuse-prone flows before understanding the key risks.

Ssd 4

Medium

• Confidence: 98% confidence
• Finding: The pricing table normalizes a chain of individually simple tasks—account creation, likes, follows, comments, reviews, and posts—that together enable scalable astroturfing, evasion, and reputation manipulation. The marketplace framing lowers friction for coordinating deceptive campaigns and makes harmful behavior easier to operationalize at volume.

VirusTotal

66/66 vendors flagged this skill as clean.