design-review
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to automate interaction with a live web environment (via a
BASE_URL) and process local HTML mockups. This creates a surface for indirect prompt injection where instructions embedded in the targeted web pages or mockups could attempt to influence the agent. - Ingestion points: Real-time browser navigation and local
design/*.htmlfiles. - Boundary markers: None specific; the skill relies on standard browser automation boundaries.
- Capability inventory: Browser navigation, clicking interactive elements, screenshotting, and reading computed CSS styles.
- Sanitization: Standard browser context isolation.
- [COMMAND_EXECUTION]: The skill mentions the use of development and automation tools including
ddev(e.g.,ddev describe) and Playwright for browser automation. These tools are used appropriately for the skill's primary purpose of environment verification and UI testing. - [EXTERNAL_DOWNLOADS]: The skill references a methodology adapted from a public GitHub repository (
OneRedOak/claude-code-workflows). This is a documentation reference for the design review standard and does not include instructions for remote code execution or automated script downloads.
Audit Metadata