Skills
Navigate
skills/shopmeskills/mcp/cn-ecommerce-search/Gen Agent Trust Hub

cn-ecommerce-search

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes a Node package @shopmeagent/cn-ecommerce-search-mcp via npx. This is a vendor-owned resource associated with the skill author 'shopme'.
  • [COMMAND_EXECUTION]: The skill uses npx to execute the MCP server command.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from e-commerce search queries and product URLs. * Ingestion points: keyword parameter in search_products tool; url parameter in get_product_detail and parse_product_link tools. * Boundary markers: None explicitly defined in the instructions to prevent the model from following instructions embedded in search terms or product data. * Capability inventory: The skill can perform network operations via the MCP server to api.shopmeagent.com. * Sanitization: No sanitization or validation of the input strings is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:07 AM