Skills
Navigate
skills/wubin1836/ai-ecommerce-expert-agent-skills/ai-ecommerce-expert-xiaohongshu-cover-image/Gen Agent Trust Hub

ai-ecommerce-expert-xiaohongshu-cover-image

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/imiva_mcp.py uses subprocess.Popen to execute shell commands to launch the MCP server environment via npx.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx -y @infimind/ecom-content-cli@latest to download and run the latest version of the Infimind e-commerce package from the npm registry at runtime.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts untrusted user input (product names, selling points, audience descriptions) which is then passed to a remote AI model via the create_koc_note_package_task tool.
  • Ingestion points: Parameters in create_koc_note_package_task such as productName, sellingPoints, and usageScenario as defined in SKILL.md.
  • Boundary markers: The skill does not implement explicit delimiters or instruction-ignore warnings for the data fields sent to the API.
  • Capability inventory: The skill has the capability to perform network requests to https://imiva.ecpro.com and generate e-commerce content based on inputs.
  • Sanitization: Inputs are serialized into JSON for transit, but no semantic sanitization or validation of the content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-xiaohongshu-cover-image