alipay-pay-for-service

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs the @alipay/agent-payment@1.0.0 package from the official npm registry. This is a vendor-owned resource provided by a well-known service. The skill includes explicit instructions for the agent to verify the package's integrity using a provided checksum before installation.
  • [COMMAND_EXECUTION]: The skill executes the alipay-bot CLI tool to interact with Alipay's payment services. The instructions include robust mitigation strategies against shell injection, such as mandatory single-quoting of all parameters and specific escaping for internal quote characters.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external payment links and transaction metadata that could originate from untrusted sources.
  • Ingestion points: Payment links matching cashier*.alipay.com or *excashier*.alipay.com, order summaries, and CLI tool responses.
  • Boundary markers: The instructions mandate strict domain validation and the use of shell-safe delimiters when processing these external inputs.
  • Capability inventory: The skill has the ability to execute CLI commands (alipay-bot), download packages (npm install), and perform network operations via the vendor tool.
  • Sanitization: Inputs are sanitized through domain whitelisting and character escaping before being used in shell commands or displayed to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 09:10 AM