audit-uiux-design-system
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and installs the Playwright CLI tool from the public npm registry during runtime to perform visual audits and capture browser screenshots.
- [REMOTE_CODE_EXECUTION]: Utilizes
npxto execute the Playwright framework, allowing the agent to run browser-based tests and interact with web pages. - [COMMAND_EXECUTION]: Executes shell commands to manage browser instances, capture visual snapshots, and monitor console logs for hydration or CSS errors.
- [PROMPT_INJECTION]: The skill researches design patterns by ingesting third-party web content through Firecrawl search results, establishing a surface for indirect prompt injection. * Ingestion points: External web content retrieved via
firecrawl:firecrawl_searchin SKILL.md. * Boundary markers: Absent; there are no explicit delimiters or instructions provided to the agent to ignore directives embedded within the research data. * Capability inventory: The skill possesses shell execution capabilities (npx), local file system access, and network research functions. * Sanitization: Absent; no validation, escaping, or filtering of the fetched external content is described.
Audit Metadata