accessibility

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @axe-core/cli package from the NPM registry. This is a well-known service and industry-standard tool for accessibility testing, posing no security risk in this context.
  • [COMMAND_EXECUTION]: Documentation includes examples for running npx lighthouse and axe CLI commands. These are standard commands for web quality auditing and are used here for educational purposes.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides guidelines for auditing external websites, which involves processing untrusted web content.
  • Ingestion points: External website source code (HTML, CSS, JS) processed by recommended CLI tools or provided to the agent for review.
  • Boundary markers: Not applicable for educational reference content.
  • Capability inventory: Shell access for executing standard audit tools (Lighthouse, axe).
  • Sanitization: Not applicable as the skill consists of instructional text and patterns rather than an automated execution pipeline.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:20 PM
Security Audit — agent-trust-hub — accessibility