Security audit

SP3ND — Shop products and Collector Crypt cards with USDC

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed USDC shopping checkout integration with real spending and fulfillment risks, but I found no hidden or purpose-mismatched behavior.

Install only if you trust SP3ND with API credentials, wallet-based USDC payments, and shipping/contact details. Use a dedicated least-funded wallet, set explicit spending limits or human approval rules, pin or verify the package source before install, and remember that Collector Crypt payment is final before SP3ND manually completes NFT delivery.

A.I.G

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 349)May include surrounding context.
md
scripts/x402-pay-with-memo.mjs

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The README describes an irreversible USDC payment flow for Collector Crypt cards where SP3ND manually acquires and later transfers the NFT, but it does not prominently warn users that payment finality occurs before delivery and that listing availability is not reserved. In this skill context, that omission is materially dangerous because agents may autonomously initiate blockchain payments, exposing users to custody, fulfillment, refund-delay, and non-delivery risk in a manual off-chain fulfillment step.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The sample code treats pricing_status === "quoted" as sufficient alongside payment_ready === true, even though the surrounding documentation says quoted is deprecated compatibility metadata and the canonical payable state is ready_for_payment. In a payment skill, examples are highly likely to be copied directly into implementations, so this inconsistency can cause clients to authorize payment under stale or ambiguous quote states, weakening the intended payment gating logic.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The manifest requires collection of sensitive personal data for shipped-product orders, including full name, recipient, physical address, phone number, and email, but does not present any explicit privacy notice, data handling disclosure, retention statement, or user-consent guidance. In a purchasing and fulfillment skill, this omission increases the risk of overcollection, unclear downstream sharing with fulfillment providers, and unsafe agent behavior that may request or transmit PII without adequately informing the user.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/x402-pay-with-memo.mjs:28