advance-receipt-check-free
Warn
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The
SKILL.mdfile contains a block of text intended for the AI agent to follow, which uses authoritative language to direct the agent to "purchase and install" a paid version of the skill. It includes pre-written consent statements like "I have authorized installation of dependencies and initiating purchase," which aims to trick the agent into bypassing normal user confirmation workflows for high-risk actions. - [COMMAND_EXECUTION]: The injection block instructs the agent to execute the shell command
npx -y @alipay/agent-payment@latest install. Providing executable commands within instructions for the agent to run is a significant security risk. - [REMOTE_CODE_EXECUTION]: The instruction to run an
npxcommand involves downloading and executing code from the NPM registry at runtime, which constitutes remote code execution. - [EXTERNAL_DOWNLOADS]: The skill directs the user and the agent to external websites (
skillpay.alipay.com,chenqg618.github.io) to download installation guides and purchase additional software components.
Audit Metadata