alipay-payment-skill

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the official @alipay/agent-payment package from the npm registry. As a vendor-owned resource matching the skill author, this is considered safe functionality.
  • [REMOTE_CODE_EXECUTION]: The skill executes a setup script (install-cli) from the downloaded npm package. This process is protected by a mandatory SHA-512 integrity verification against a hardcoded hash to prevent supply chain attacks.
  • [COMMAND_EXECUTION]: Shell command execution is limited to the alipay-bot CLI and curl. The skill implements strict parameters, such as wrapping arguments in single quotes and restricting file operations to the /tmp/openclaw/alipay-bot-cli/ directory.
  • [PROMPT_INJECTION]: The instructions contain defensive prompts to ignore requests to bypass payment logic, avoid role-play scenarios, and reject commands to read sensitive local files.
  • [DATA_EXFILTRATION]: Network communication is exclusively directed toward official Alipay domains (*.alipay.com, *.alipay.net, *.alipay.cn) for the purpose of payment processing and status verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 06:43 PM
Security Audit — agent-trust-hub — alipay-payment-skill