The Agent Skills Directory

[SAFE]: The skill consists of instructional text and Python code snippets for creating various omics-related plots (Volcano, MA, Heatmap, GSEA, etc.). All operations are performed on local datasets and save results to a local workspace directory (figures/).
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from local CSV/TSV files.
Ingestion points: Files are read using pd.read_csv() across all plotting recipes (e.g., deg_results.csv, expression.csv, gwas.csv).
Boundary markers: Absent. The skill provides code templates to be populated with data.
Capability inventory: The skill uses matplotlib and seaborn for visualization and pandas for data manipulation. It performs file writes to the local figures/ directory.
Sanitization: Standard numeric and string processing via numpy and pandas. Data labels are converted to strings before plotting. The risk of these labels influencing subsequent agent behavior is minimal in a visualization context.

omics-plotting