frontend-design-review
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
npx playwrightfor capturing screenshots andnpx playwright install chromiumfor setting up the environment. It also suggests usinggit diff --checkto verify file changes. These commands are used as intended for the skill's functional purpose. - [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by reading and processing content from external URLs and various project files such as
src/,DESIGN.md, andPRODUCT.md. - Ingestion points: Project source code, documentation files, and web content from user-provided URLs.
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading these external files.
- Capability inventory: The agent can read and write to the file system and execute shell commands via
npx playwrightandgit. - Sanitization: The instructions do not define methods for sanitizing or validating the content extracted from external sources.
- [EXTERNAL_DOWNLOADS]: The skill recommends installing Chromium via Playwright. As Playwright is an official tool from Microsoft, this is a standard operation for visual testing and quality assurance workflows.
Audit Metadata