The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for the AI model to improve clarity in communication when a user fails to understand a previous response.
[NO_CODE]: No executable scripts, binaries, or shell commands are included in the skill files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (agent reports and user messages) to re-pitch them. While this constitutes an attack surface, the skill does not use any sensitive tools or perform dangerous operations that could be exploited via injection.

wait-what