gemini-agent-dev-support
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides coding standards aimed at improving security, such as requiring server-side API key management and using DOMPurify to sanitize markdown rendering.
- [EXTERNAL_DOWNLOADS]: The README provides a command to install the skill using
npx skills addfrom a GitHub repository associated with the author (drgarbage/ag-course-index). This is standard behavior for skill distribution on this platform. - [COMMAND_EXECUTION]: The skill contains example JavaScript and Node.js code snippets for handling user input (IME), calling the Google Generative AI SDK, and error handling. These are instructional templates and do not execute dangerous system commands.
- [PROMPT_INJECTION]: The instructions provide architectural constraints for the AI to follow during planning, such as preventing the use of legacy SDKs and ensuring local development environments do not use insecure file protocols.
Audit Metadata