ai-ecommerce-expert-model-product-main-image

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the '@infimind/ecom-content-cli' package from the NPM registry at runtime using the 'npx' command. This is a vendor-owned resource required for interaction with the IMIVA platform.
  • [REMOTE_CODE_EXECUTION]: The skill executes remote code from the NPM registry using 'npx -y'. The dependency is not pinned to a specific version, utilizing the '@latest' tag, which presents a potential supply chain risk.
  • [COMMAND_EXECUTION]: The script 'scripts/imiva_mcp.py' uses 'subprocess.Popen' to invoke the Node.js CLI tool. This is the intended method for executing the skill's tasks within the user environment.
  • [PROMPT_INJECTION]: The skill processes user-supplied data such as product descriptions and images, which creates a surface for indirect prompt injection.
  • Ingestion points: Arguments for the 'create_product_main_image_task' tool, including 'productImages', 'coreSellingPoints', and 'usageScenario' in 'SKILL.md'.
  • Boundary markers: The skill instructions in 'SKILL.md' direct the agent to verify all product facts and use only user-confirmed information.
  • Capability inventory: The skill possesses command execution and network access capabilities through the 'imiva_mcp.py' script and the underlying CLI tool.
  • Sanitization: There is no evidence of explicit sanitization or filtering of the input arguments in the Python wrapper before they are passed to the external tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:02 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-model-product-main-image