skills/kensaurus/skills/audit-ux/Gen Agent Trust Hub

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 npx to facilitate accessibility testing during the audit process.
  • [REMOTE_CODE_EXECUTION]: Executes the downloaded Playwright package directly via npx to 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_search and firecrawl:firecrawl_scrape tool calls in SKILL.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
Risk Level
SAFE
Analyzed
Oct 19, 2026, 06:51 PM