shopify-mcp

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of data from external Shopify APIs, which introduces a surface for indirect prompt injection. \n
  • Ingestion points: Data retrieved via Admin and Storefront API tools (e.g., product descriptions, customer info).\n
  • Boundary markers: Although the implementation uses structured data, there are no explicit instructions to the agent to treat this external content as untrusted.\n
  • Capability inventory: The skill has permissions to read and modify store data, such as inventory and carts.\n
  • Sanitization: The provided examples do not include logic for sanitizing or validating external data before processing.\n- [EXTERNAL_DOWNLOADS]: The skill instructions involve downloading and executing the official Shopify developer toolkit (@shopify/dev-mcp) via the npm registry.\n- [COMMAND_EXECUTION]: Modifies the local configuration file at ~/.claude.json/mcpServers to register the MCP server, enabling persistence across agent sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 04:19 AM
Security Audit — agent-trust-hub — shopify-mcp