browser-tools

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several system commands to manage the sandboxed browser environment. This includes using rsync for copying profile data to an isolated directory, where profile names are validated to prevent directory traversal. It also uses sqlite3 to modify the copied profile's database to remove Google cookies, preventing session conflicts. Standard process management involves using ps for process discovery and process.kill for stopping owned instances, following strict verification of the process command line and managed state.
  • [COMMAND_EXECUTION]: The eval.mjs tool allows for the execution of arbitrary JavaScript in the browser tab context using Puppeteer. This is an intended core feature and is used to interact with web page content.
  • [EXTERNAL_DOWNLOADS]: The skill's setup process involves installing the @rezkam/browser-tools package from npm. As this package is provided by the skill's author ('rezkam'), it is a vendor-owned resource necessary for the skill's operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 11:11 PM
Security Audit — agent-trust-hub — browser-tools