Back to skill

Security audit

Alipay Aipay Product Intro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Alipay product-introduction workflow that makes a fixed request to Alipay and may hand off a paid-resource response to a payment skill.

Before installing, understand that asking for this product introduction can cause the agent to contact an Alipay endpoint and may lead to a paid HTTP 402 flow handled by another Alipay payment skill. Only proceed with payment when the payment step and amount are clear to you.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The manifest description says the skill should be used when the user wants product introductions related to Alipay AI payment, and includes a broad condition like '用户想了解支付宝智能体钱包功能'. This lacks clear exclusion conditions or negative examples, so ordinary product questions beyond the intended narrow introduction flow could trigger the skill unintentionally.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to send an external network request to aipayapi.alipay.com via curl without first clearly informing the user that data will be transmitted off-platform. Even though the request appears to be a simple GET with no explicit user secrets, silent outbound requests can violate user expectations, create privacy concerns, and establish a risky precedent for agent-initiated network access.

Static analysis

No suspicious patterns detected.