Web agents don't see pages like humans do ā they
read the full DOM, including hidden text designed
to hijack their goals.
Guni scans raw HTML before your agent executes and
returns ALLOW / CONFIRM / BLOCK with evidence.
Detects:
ā Prompt injection
ā Phishing forms
ā Goal hijacking
ā Clickjacking
ā Redirect abuse
ā Deceptive UI
Works with Playwright, browser-use, and LangChain.
Free to self-host (MIT). Hosted API from ā¹999/mo.
