ai-ecommerce-expert-instagram-ecommerce-content

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the execution of the @infimind/ecom-content-cli package from the official NPM registry via npx. This is a vendor-managed resource provided by Beijing Jiruikeji to facilitate e-commerce content production.
  • [COMMAND_EXECUTION]: The Python script scripts/imiva_mcp.py uses subprocess.Popen to launch the npx command. This is the intended mechanism for the agent to interact with the Model Context Protocol (MCP) server provided by the vendor.
  • [DATA_EXPOSURE]: The skill uses an MCP_TOKEN for authentication. The instructions correctly advise users to store this sensitive token in local environment variables rather than hardcoding it, aligning with standard secret management practices.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text such as product selling points and target audience descriptions to generate marketing copy.
  • Ingestion points: Data enters the system through tool arguments like sellingPoints and productName in SKILL.md and the Python script.
  • Boundary markers: Data is encapsulated within JSON-RPC payloads before being passed to the CLI tool.
  • Capability inventory: The skill uses subprocess execution and network requests (via the vendor CLI) to interact with the IMIVA API.
  • Sanitization: Input validation is deferred to the vendor's API and the CLI tool's argument parsing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-instagram-ecommerce-content