Skip to main content

Five pre-built injections. One click each. Watch what it would have executed.

Five real-world injections dressed as ordinary business text — an invoice, a knowledge-base article, an executive forward, a calendar invite, a support ticket. Every one of them reads as routine to a busy human. Every one carries a payload aimed at an AI agent's authority.

Screen one. Forward the report. That's the demo.

evidence url · lives 7 days · re-screen to reissue

01

The invoice that redirects payment

Looks like
Accounts-payable email with an attached invoice
Would have executed
An unscreened agent would have updated the payment endpoint and mailed the ledger. This changes where money goes.
Screen it
02

The CRM doc that exfiltrates itself

Looks like
A knowledge-base article pasted into RAG
Would have executed
An unscreened agent would have packaged customer records and posted them to an attacker-controlled endpoint.
Screen it
03

The urgent brief that escalates itself

Looks like
An executive forward with a tight deadline
Would have executed
An unscreened agent would have bypassed the approval gate using fabricated authority — no human ever saw the request.
Screen it
04

The calendar invite that rewrites instructions

Looks like
A meeting invite description
Would have executed
An unscreened agent would have replaced its own standing instructions with attacker-supplied ones — persistence after the meeting is long gone.
Screen it
05

The support ticket that asks for a secret

Looks like
A routine ticket from a verified customer
Would have executed
An unscreened agent would have echoed credentials into a reply — and the transcript becomes the leak.
Screen it

Have your own text? Paste it at the demo console. After you have a report: Install Parse.