agent-browser

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: All documented commands (open, snapshot, click, fill, screenshot, etc.) are standard for browser automation and match the skill's stated purpose.
  • [SAFE]: No prompt injection markers, obfuscated content, or unauthorized network operations to non-whitelisted domains were detected.
  • [SAFE]: The skill does not attempt to access sensitive local files or perform privilege escalation; file operations like 'state save' and 'screenshot' are used for legitimate session management and output.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 03:38 PM