ai-ecommerce-expert-promotion-poster

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/imiva_mcp.py uses subprocess.Popen to invoke the Node Package Runner (npx). The command is executed using a list of arguments [npx, "-y", PACKAGE], which effectively prevents shell injection by avoiding the use of a shell string and unvalidated user input in the command itself.
  • [EXTERNAL_DOWNLOADS]: The skill configuration and helper script utilize npx -y @infimind/ecom-content-cli@latest. This command fetches and executes the latest version of the specified package from the npm registry. This is the intended functional mechanism for the skill to interact with the IMIVA ecommerce content platform.
  • [CREDENTIALS_SAFE]: The skill follows security best practices for credential handling. It requires an MCP_TOKEN to be set in the local environment and explicitly instructs users not to hardcode this token in the skill, chat logs, or configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-promotion-poster