ton-send
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for legitimate cryptocurrency wallet interactions. It includes explicit instructions to confirm transactions with the user before execution, which is a critical security control for financial operations.
- [PROMPT_INJECTION]: No instructions attempting to bypass safety filters or override agent behavior were identified. The workflow follows a logical sequence for asset transfer.
- [DATA_EXFILTRATION]: No evidence of unauthorized data access, credential harvesting, or transmission of sensitive data to external servers was found.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts or packages. It relies entirely on pre-defined MCP tools for blockchain interaction.
- [COMMAND_EXECUTION]: The skill uses structured tool calls rather than arbitrary shell commands. No dangerous system-level command execution patterns were detected.
Audit Metadata