First Dollar

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.0.4

Overview

This wallet-teaching skill is mostly transparent, but some guidance can expose private keys or wallet files if followed carelessly.

Use only with a dedicated low-balance wallet. Do not paste private keys, seed phrases, keyfile contents, raw environment output, or wallet files into chat; prefer wallet status commands that show only addresses and balances, and avoid putting private keys directly on command lines.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Intent-Code Divergence

Medium

• Confidence: 92% confidence
• Finding: The skill tells users to inspect local wallet files, config files, and environment variables while framing itself as only explanatory. In a wallet-focused skill, those instructions are sensitive because they normalize handling secret-bearing locations and can lead users to expose private keys, keyfiles, or wallet metadata into the chat or logs.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The instructions explicitly advise users to search their environment for private-key variables without warning them not to print, paste, or disclose the values. In an agent skill context, this is especially dangerous because users may follow the command and then share the output with the agent, directly leaking spend authority for their wallet.

VirusTotal

67/67 vendors flagged this skill as clean.