The Agent Skills Directory

[SAFE]: The skill provides a professional and rigorous methodological framework for data analysis. It incorporates best practices for data integrity, such as verification gates, reconciled control totals, and analytical quality rubrics. It also includes explicit guidance on data privacy and PII (Personally Identifiable Information) minimization.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted datasets (e.g., CSV, SQL tables, and spreadsheets), which represents an attack surface for indirect prompt injection.
Ingestion points: Data enters the agent's context through datasets supplied by the user as described in SKILL.md and references/data-collection.md.
Boundary markers: Instructions in SKILL.md explicitly mandate keeping skill guidance, project objectives, and dataset evidence in separate layers.
Capability inventory: The agent has the capability to execute SQL, perform data transformations, and generate analytical reports or dashboards.
Sanitization: The methodology requires a dedicated 'Data Understanding' stage and data quality profiling (as detailed in references/data-quality.md) to assess record semantics and validity before analysis begins, providing procedural defense against malicious data content.

data-analyst