ai-ecommerce-expert-1688-ecommerce-content

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 the npx utility on the host system to interact with the IMIVA service.
  • [EXTERNAL_DOWNLOADS]: The skill uses npx -y @infimind/ecom-content-cli@latest to fetch the necessary CLI tool from the npm registry during execution.
  • [REMOTE_CODE_EXECUTION]: By downloading and immediately running the @infimind/ecom-content-cli package, the skill performs remote code execution from an external source.
  • [DATA_EXPOSURE]: The skill utilizes a sensitive authentication token (MCP_TOKEN) sourced from environment variables, which is passed to the subprocess environment to enable API access.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted product data (images, selling points, scenarios) which is interpolated into parameters for the external content generation service. While the script validates the JSON structure, it lacks explicit boundary markers to prevent the agent from being influenced by malicious instructions embedded in the product descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-1688-ecommerce-content