Back to skill

Security audit

USDG x402 Payments — Robinhood Chain

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed payment helper for small USDG x402 API charges, with clear limits and confirmation rules around higher-risk payments.

Install only if you intend to let an agent spend small amounts of USDG for x402 API calls. Use a dedicated low-balance wallet, keep EVM_PRIVATE_KEY out of logs and prompts, verify the gateway and contract constants, and require manual review for larger or fund-moving operations.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
**Why USDG on Robinhood Chain is the easiest x402 rail:**

- **No approval step, no gas.** USDG implements EIP-3009
  (`transferWithAuthorization`), so there is no allowance to grant and no
  Permit2 dance. The payer wallet needs USDG only — the gateway's
  facilitator pays the gas.
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.