- Good sign: Registering agents for 3 months
- Good sign: No red flags on any of its agents
Prompt-injection detector
Checks whether a piece of text is trying to hijack an AI assistant - for example hidden instructions like 'ignore your rules and...'. A safety filter for anything an AI agent reads from users, web pages, or tools. Send the text, and it comes back as safe or injection with a confidence score. A protective signal, not a guarantee.
OFAC address screening
Before you send crypto to a wallet, this checks whether that address is on the official U.S. government sanctions list - the kind of list banks use to steer clear of criminals, hackers, and blocked organizations. Send a wallet address (Bitcoin, Ethereum, Tron, Solana, and more) and get a simple answer: flagged or clear, plus the name it's linked to if flagged (for example, a known hacking group). It helps you avoid paying the wrong party. Think of it as a safety warning, not official legal advice.