amazon-kdp
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the AI agent to execute several shell commands to establish the environment, including installing dependencies, starting a local Express server, and running task-specific CLI scripts.
- [EXTERNAL_DOWNLOADS]: During setup, the skill performs downloads of Node.js packages from the NPM registry and fetches the Chromium browser binary through the Playwright framework.
- [REMOTE_CODE_EXECUTION]: The automation logic employs browser-side code execution by injecting local JavaScript files into the Chromium instance to parse and interact with KDP web interfaces.
- [SAFE]: The skill implements essential safety features including a 4-second request delay to prevent rate-limiting and a local data persistence model that ensures Amazon session cookies are never transmitted to external servers.
Audit Metadata