test-site

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [Command Execution]: The skill utilizes the Bash tool to execute local utility scripts (check-version.js, check-activation-status.js) stored within the plugin's environment. These scripts are used for configuration checks and version verification.
  • [Dynamic Script Execution]: The skill employs browser_evaluate to run JavaScript within the browser context of the target site. This is used for extracting internal links to support the crawling process.
  • [Processing of External Content]: The skill ingests data from external URLs provided by the user, including accessibility snapshots, console messages, and network request metadata. It implements a 25-page crawl limit to ensure the operation remains within a defined scope.
  • [Manual Authentication Handling]: The skill is designed to avoid automated credential handling. It specifically instructs the agent to ask the user to log in manually via the browser when authentication is required, which prevents the exposure of sensitive login information to the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 11:10 AM