browser-trace

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of the browse CLI to capture browser state (screenshots, DOM, CDP events) and manage remote sessions. These commands are executed using Node.js spawn and execFileSync with argument arrays, which is the recommended security practice for preventing command injection.
  • [EXTERNAL_DOWNLOADS]: The skill includes scripts to retrieve session artifacts such as logs and downloaded files from the Browserbase cloud platform via its official CLI. These operations are consistent with the skill's stated purpose and target the vendor's own infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 05:54 AM
Security Audit — agent-trust-hub — browser-trace