accessibility

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No security issues detected. The skill is entirely instructional, providing guidance on semantic HTML, keyboard navigation, and accessibility auditing.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network operations were identified.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill suggests using industry-standard tools like axe-core and Lighthouse for auditing but does not include any automated installation scripts or remote execution commands.
  • [Indirect Prompt Injection] (LOW): The skill is designed to process and modify application source code for accessibility improvements. This creates an ingestion surface for untrusted data, but it is a necessary part of the skill's functionality and lacks associated high-risk capabilities like data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 08:27 PM