skills/qu-skills/skills/agent-browser/Gen Agent Trust Hub

agent-browser

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill implements an execute function that runs arbitrary JavaScript code within the browser context. This is a standard requirement for advanced web scraping and automation tasks.- [COMMAND_EXECUTION]: The interact action supports the upload method, which allows the agent to select local files for upload to web applications as part of form automation.- [EXTERNAL_DOWNLOADS]: The skill's documentation guides the installation of the belt-sh/cli tool using npx and references configuration files hosted on the inference-sh GitHub organization, which is the platform's official repository.- [SAFE]: The documentation explicitly includes a 'Security Best Practices' section in references/authentication.md that warns against hardcoding credentials and demonstrates the use of environment variables and secrets managers. It also emphasizes the importance of closing sessions to release resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:37 PM
Security Audit — agent-trust-hub — agent-browser