wcag-audit-patterns

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references well-known, legitimate accessibility testing tools and libraries including axe-core, pa11y, and lighthouse via official npm and npx channels.
  • [COMMAND_EXECUTION]: Provides informational shell commands for executing accessibility audits with established CLI tools.
  • [PROMPT_INJECTION]: Auditing third-party websites introduces an indirect prompt injection risk where malicious instructions could be embedded in the HTML content being analyzed.
  • Ingestion points: Website source code, UI elements, and accessibility trees fetched during automated or manual scans.
  • Boundary markers: No explicit delimiters are suggested in the instructions to separate the agent's audit instructions from the content being audited.
  • Capability inventory: The implementation playbook describes script-based audit capabilities and the use of CLI testing tools.
  • Sanitization: No explicit sanitization or filtering of the audited content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 06:51 AM