The Agent Skills Directory

[SAFE]: The skill implements a comprehensive safety protocol requiring the agent to display transaction details (amounts, chains, recipients, and fees) and obtain explicit user confirmation before executing any bridge or swap operations.
[SAFE]: A specific warning mechanism is established for 'External Bridges' (transfers to non-user-owned wallets), ensuring the user is informed that such funds cannot be recovered if the address is incorrect.
[SAFE]: The instructions explicitly mitigate indirect prompt injection risks by mandating that recipients or transaction targets originating from untrusted content (like web pages or previous tool outputs) must be re-confirmed by the user.
[SAFE]: All network operations are directed to the vendor's infrastructure or well-known technology services associated with the skill's primary purpose.

openfin-relay