accessibility

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for running accessibility audits using npx lighthouse and the axe command-line interface. These are standard developer tools used for legitimate testing and verification of web standards.
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of @axe-core/cli from the npm registry. This is a well-known and reputable package maintained by Deque Systems for automated accessibility testing.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external web source code (HTML, CSS, and JavaScript) to perform audits. While this represents a potential ingestion surface for indirect prompt injection, the skill includes explicit 'Anti-Patterns' that instruct the agent not to treat external content as trusted instructions. It also provides a 'Verification Protocol' to ensure outputs are based on evidence and local tests rather than untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 01:38 AM
Security Audit — agent-trust-hub — accessibility