acp-checkout-mcp

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a design document for mapping Agentic Commerce Protocol (ACP) operations to Model Context Protocol (MCP) tools, providing a conceptual framework rather than executable code.
  • [EXTERNAL_DOWNLOADS]: Directs the agent to fetch reference material from well-known and trusted developer documentation sites, including OpenAI's commerce specifications and the official MCP SDK repositories.
  • [COMMAND_EXECUTION]: No suspicious or arbitrary command execution patterns were identified; the use of bash and other tools is consistent with the developer-focused nature of building an MCP server.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 06:09 AM