PaySpawn — On-Chain Spending Limits for AI Agents

• Outcome: Pass
• Latest audit: May 28, 2026, 7:39 AM
• Version:
  1.0.0

Overview

This is a documentation-only payment SDK skill that openly describes capped USDC spending, credentials, whitelists, and kill switches, with no hidden code or deceptive behavior found.

Install only if you intend to let an agent make limited on-chain USDC payments. Verify that you trust PaySpawn and @payspawn/sdk, use a dedicated low-balance wallet or credential, set strict daily and per-transaction caps, enable recipient or domain allowlists, and require approval before direct payments, fleet provisioning, or sending sensitive data to paid APIs.

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: 93% confidence
• Finding: The skill explicitly demonstrates automatic paid HTTP requests and direct USDC payments, but it does not include a clear warning that these actions can spend real funds and transmit data to third-party endpoints. In an agent-skill context, users may copy these examples verbatim, causing unintended on-chain payments or disclosure of request contents to external services.

VirusTotal

65/65 vendors flagged this skill as clean.