audit-ux
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the Playwright CLI tool from the npm registry using
npxto facilitate accessibility testing during the audit process. - [REMOTE_CODE_EXECUTION]: Executes the downloaded Playwright package directly via
npxto perform UI snapshots and keyboard navigation tests. - [COMMAND_EXECUTION]: Uses shell commands to invoke Playwright for automated browser interactions and accessibility verification.
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes content from external UX research domains including nngroup.com and lawsofux.com.
- Ingestion points: Data returned from
firecrawl:firecrawl_searchandfirecrawl:firecrawl_scrapetool calls inSKILL.md. - Boundary markers: Absent; the skill does not wrap external scraped content in delimiters or provide specific instructions to the agent to ignore potentially malicious embedded content.
- Capability inventory: The skill possesses shell execution capabilities (
npx), read access to project source files (*.tsx), and browser control tools. - Sanitization: Absent; no explicit sanitization or filtering of the retrieved web content is performed before processing.
Audit Metadata