The Agent Skills Directory

[SAFE]: The skill implements a secure transaction flow by requiring a mandatory user confirmation step before calling the high-privilege send_raw_transaction tool.
[SAFE]: No patterns of prompt injection, data exfiltration, or unauthorized command execution were detected in the instructions.
[SAFE]: The skill does not download external code, install third-party packages, or use dynamic code execution functions like eval or exec.
[SAFE]: No obfuscation, hidden characters, or deceptive metadata patterns were found in the skill file.

ton-swap