The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for conversational behavior. It does not contain any executable scripts, shell commands, or external dependencies.
[SAFE]: No network operations, file system access, or credential usage were detected. The skill is isolated to the chat context.
[SAFE]: The configuration explicitly includes disable-model-invocation: true, which restricts the agent from calling external tools or other AI models, further limiting the potential attack surface.
[SAFE]: There are no signs of obfuscation, prompt injection, or persistence mechanisms. The instructions focus on mirroring user input to facilitate 'rubber duck' debugging.

rubber-duck