skills/alipay/ai/alipay-aipay/Gen Agent Trust Hub

alipay-aipay

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell scripts and system utilities to automate project scanning and integration testing as part of its primary payment integration functionality.
  • references/integration/modules/scripts/local_402_sandbox_pay.py executes curl to interact with local developer services and the Alipay sandbox environment.
  • references/normal/scripts/integration_message_runner.mjs spawns child processes to run the project_route_inspector.sh script for identifying payment-related code markers.
  • [EXTERNAL_DOWNLOADS]: The skill handles the acquisition of official developer resources from authorized vendor locations.
  • It provides instructions for downloading the official alipay-cli utility from the vendor's dedicated domain (opengw.alipay.com).
  • references/onboarding/modules/scripts/download_key_tool.sh downloads official key management tools for macOS and Windows to the user's local machine.
  • [REMOTE_CODE_EXECUTION]: The skill incorporates self-management and setup procedures using remote vendor-controlled sources.
  • references/normal/self-update.md implements a self-update mechanism using npx to ensure the skill and its components are current.
  • The installation instructions for the vendor's CLI tool involve executing a setup script directly from an official Alipay subdomain.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection common in tools that process external data headers.
  • Ingestion points: references/integration/modules/scripts/local_402_sandbox_pay.py retrieves and decodes protocol headers from a user-specified local service during the sandbox testing phase.
  • Boundary markers: Decoded data is displayed in the terminal output without specific delimiters separating external content from system instructions.
  • Capability inventory: The skill has capabilities for network communication, file system writes for configuration storage, and command execution.
  • Sanitization: The skill mitigates potential exposure by automatically redacting sensitive fields like signatures and payment proofs before displaying results.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 07:24 AM
Security Audit — agent-trust-hub — alipay-aipay