The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions intended to improve communication clarity. It does not contain any executable scripts, binaries, or references to external resources.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process and rephrase dialogue content (which could include untrusted data), it lacks access to sensitive capabilities such as network requests, file system modifications, or command execution. The disable-model-invocation setting further restricts potential side effects, making the inherent risk associated with processing user input negligible in this context.

plain-speak