utility-meter-reading-check-free

Warn

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: MEDIUMPROMPT_INJECTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The SKILL.md file contains a template message designed to be provided to an AI agent which includes the phrase "我已授权安装依赖和发起购买" (I have authorized installing dependencies and initiating purchases). This is an attempt to override an agent's standard safety protocols and user confirmation requirements by pre-claiming authorization for high-risk actions.
  • [REMOTE_CODE_EXECUTION]: The documentation instructs the AI agent to execute the shell command npx -y @alipay/agent-payment@latest install. The npx utility downloads and executes external code from a remote registry at runtime, which is a vector for remote code execution and bypasses local code auditing.
  • [EXTERNAL_DOWNLOADS]: The skill documentation provides links to external websites for the purpose of purchasing expanded software versions, including URLs hosted on skillpay.alipay.com and a personal GitHub Pages site at chenqg618.github.io.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 16, 2026, 11:28 AM
Security Audit — agent-trust-hub — utility-meter-reading-check-free