Browser Daemon

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The daemon script allows for the execution of arbitrary JavaScript within the browser context.
  • Evidence: In browser-daemon.js, the exec action directly passes user-provided code to Playwright's page.evaluate() method.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a significant attack surface for instructions embedded in external web content.
  • Ingestion points: Data enters the agent's context through the content of pages navigated to via page.goto and browser console logs captured by the daemon in browser-daemon.js.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands in the processed web content.
  • Capability inventory: The skill has the capability to execute JavaScript in the browser, read page content, and interact with the local file system for IPC.
  • Sanitization: No validation or sanitization is performed on the data retrieved from external URLs before it is processed or displayed.
  • [COMMAND_EXECUTION]: The skill requires manual execution of Node.js scripts to start the daemon and provides client scripts that are intended to be executed from the command line.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 08:17 PM
Security Audit — agent-trust-hub — Browser Daemon