ai-ecommerce-expert-zero-basis-case-learning

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/imiva_mcp.py uses subprocess.Popen to execute npx. This is used to wrap the official IMIVA MCP command-line interface for tool invocation.
  • [EXTERNAL_DOWNLOADS]: The skill configuration and helper scripts utilize npx -y @infimind/ecom-content-cli@latest to fetch and run the official vendor package from the NPM registry. This ensures the latest version of the content generation tools is available.
  • [REMOTE_CODE_EXECUTION]: The use of npx to execute a remote package constitutes remote code execution. This behavior is the primary intended mechanism for the skill to interact with the IMIVA platform and targets the official package provided by the service vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection as it ingests user-supplied prompts and image paths in the create_smart_refine_task function. No specific exploits were found, but the agent processes external content as part of its core workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-zero-basis-case-learning