skills/raphaelsalaja/skills/keyboard/Gen Agent Trust Hub

keyboard

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses a self-contained JavaScript script (tabstops.js) to audit the Document Object Model (DOM) for accessibility. This script collects element metadata such as ARIA roles, names, and positions for the sole purpose of reporting accessibility findings.
  • [SAFE]: Analysis of the source code confirms there are no network operations, external downloads, or data exfiltration patterns. All collected data remains within the browser context or is reported back to the user as requested.
  • [SAFE]: The skill implements security best practices by including platform configuration (disable-model-invocation: true) to restrict model behavior during execution and requires explicit triggers for browser evaluation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 02:32 PM