wcag-audit-patterns

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as an educational and procedural guide for accessibility auditing. All code snippets and command examples provided are standard for the industry and align with the skill's primary purpose of WCAG compliance testing.
  • [COMMAND_EXECUTION]: The implementation playbook includes documentation for using common command-line interfaces (CLI) for automated testing, such as npx @axe-core/cli, npx pa11y, and lighthouse. These tools are legitimate and widely used for scanning web pages for accessibility issues.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from external websites by running automated scans and manual checks. This ingestion of untrusted content represents a potential surface for indirect prompt injection, where a site could include malicious instructions in HTML comments or metadata. However, the risk is mitigated by the skill's specific focus on mapping findings to fixed WCAG criteria and remediation patterns.
  • [REMOTE_CODE_EXECUTION]: The skill provides templates for using axe-core within test runners like Playwright. The script injection (page.addScriptTag) is a standard testing pattern for accessibility auditing and does not involve untrusted remote sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 06:09 AM