The Agent Skills Directory

[SAFE]: The skill follows secure design principles for financial operations by mandating that transactions be emulated for preview and explicitly confirmed by the user before broadcasting via send_raw_transaction.
[NO_CODE]: The skill contains markdown instructions and platform configuration only, with no executable scripts or binary files provided.
[SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were identified. Input ingestion points for wallet addresses and domains are handled through dedicated blockchain tools with a mandatory manual confirmation step which effectively mitigates indirect prompt injection risks.

ton-send