shopify-product-images

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to add an MCP server from the vendor's domain https://mcp.apimage.org/mcp. This is a legitimate vendor resource necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: Provides a setup command (claude mcp add) for integrating the apimage tool via the Model Context Protocol. The command uses a placeholder for the API key, following safe practice.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that ingests product photos. While external data ingestion presents a theoretical surface for indirect injection, it is managed as part of the core image processing functionality.
  • Ingestion points: Ingests product photos through the product[\"photo\"] variable in the SKILL.md code snippet.
  • Boundary markers: None present in the conceptual code snippet.
  • Capability inventory: Utilizes remove_background and generate_image tools.
  • Sanitization: Not explicitly defined in the brief conceptual example code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 08:39 AM