getyo.dev

This server isn't on gate's handpicked list. That's not necessarily bad, but there's no third-party signal about it — review its tools carefully.

The description tells the AI to 'store it immediately in your secret mechanism' and 'MUST show the user' the paired_with account. This is a reasonable operational instruction for a pairing flow, but it's worth noting this is an embedded directive to the agent rather than pure data; verify it doesn't get used to suppress showing paired_with in some flows or to store the key in an insecure location. Overall benign but should be monitored since it directs agent behavior beyond simple data return.

The context_url parameter allows the tool to specify an https or app deep-link URL that opens when the user taps the notification. While described as content-free, this could be used to direct users to arbitrary URLs (phishing risk) if the calling agent is compromised or manipulated. Not a prompt-injection risk per se, but a capability that should be validated/sanitized (e.g., domain allowlisting) given it's user-facing and could be abused for phishing if the agent's inputs are attacker-influenced.