shopify-products
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill supports gathering product information via website scraping from user-provided URLs. This introduces a potential surface for indirect prompt injection, as malicious instructions on a scraped website could attempt to influence the agent's actions. \n
- Ingestion points: Step 1 (Website scraping from external URLs). \n
- Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' commands for the scraped content. \n
- Capability inventory: Use of shell commands (
curl) and potentially destructive Shopify GraphQL mutations (productDelete). \n - Sanitization: Absent. No validation or escaping of the scraped content is described before use. \n- [COMMAND_EXECUTION]: The skill provides examples for using
curlto interact with the Shopify Admin API to perform product management and image upload tasks.
Audit Metadata