The Agent Skills Directory

[SAFE]: The skill is entirely instruction-based and does not include any executable code, shell scripts, or external dependencies. It focuses on guiding the AI through the process of generating SEO dashboards and executive summaries.
[DATA_EXPOSURE]: The skill reads and writes state information from a local memory/ directory and CLAUDE.md. This is a standard workflow for maintaining project context and does not involve accessing sensitive system credentials or private user files.
[PROMPT_INJECTION]: There are no patterns suggesting an attempt to bypass agent safety filters or override core instructions. The prompts are strictly related to report formatting and data interpretation.

performance-reporter