apps-inspect-payments
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured guidance for using MCP (Model Context Protocol) tools to query a legitimate payment service (theapps.jp). All external URLs point to the official documentation and webhook schemas of the service provider.
- [SAFE]: The instructions emphasize least privilege and data privacy, explicitly directing the agent to retrieve only the smallest amount of data needed, avoid reproducing raw customer records, and omit unrelated personal fields in responses.
- [SAFE]: There are no instances of command execution, remote code downloads, or credential harvesting. The skill correctly identifies that it does not possess tools for sensitive operations like refunds or cancellations.
Audit Metadata