ai-ecommerce-expert-scene-product-main-image

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the npx command to download and execute the @infimind/ecom-content-cli package from the official NPM registry. This package is the official tool for the IMIVA e-commerce platform described in the skill metadata.
  • [COMMAND_EXECUTION]: The Python script scripts/imiva_mcp.py uses subprocess.Popen to execute the downloaded MCP tool. This allows the agent to perform actions such as creating image generation tasks and checking user credits via the command line.
  • [CREDENTIALS_UNSAFE]: The skill follows security best practices by instructing users to store their authentication tokens in the MCP_TOKEN environment variable rather than hardcoding them into the skill scripts or configuration files.
  • [PROMPT_INJECTION]: The skill accepts user-provided content (product categories, selling points, and usage scenarios) which are interpolated into tool arguments. While this represents a surface for indirect prompt injection, the risk is mitigated by the structured nature of the data passed to the IMIVA API.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-scene-product-main-image