skills/drolu/agent-skills/browser-use/Gen Agent Trust Hub

browser-use

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill implements secure API key management using the 'OPENROUTER_API_KEY' environment variable and provides a 'sensitive_data' mechanism to use credentials without exposing them to the LLM context.
  • [COMMAND_EXECUTION]: Documentation provides examples of custom actions for interacting with the local filesystem ('save_data') and executing SQL queries ('query_db'), which are standard extension points for users to build functional automation tools.
  • [EXTERNAL_DOWNLOADS]: The skill instructions specify the installation of the 'browser-use' and 'langchain-openai' packages from public registries and the automated download of Chromium via Playwright.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 07:10 PM
Security Audit — agent-trust-hub — browser-use