frontend-ui-ux-wizard
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs shell operations to build projects, manage git repositories, and execute hosting platform CLIs for deployment.
- [EXTERNAL_DOWNLOADS]: Fetches and installs development tools such as Playwright and platform-specific CLIs from well-known, official package registries and vendor domains.
- [PROMPT_INJECTION]: Identified an indirect prompt injection surface in Step 1b, where the skill uses a headless browser to capture screenshots of external or local web pages, potentially exposing the agent to untrusted instructions within the rendered content.
- [SAFE]: Includes explicit hard rules to safeguard sensitive data, ensuring that environment files and secrets are not committed to version control systems.
Audit Metadata