The Agent Skills Directory

[SAFE]: The skill provides instructions and Python code templates for performing lipid class enrichment analysis. The code uses standard, trusted libraries (pandas, scipy) and follows legitimate scientific data processing patterns without any suspicious operations or hidden intent.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing user-supplied lipidomics results (lists of lipids and fold-change data). While this is a data ingestion surface, the risk is negligible as the data is treated as structural/statistical input for calculations and API lookups, with no path to arbitrary command execution or privilege escalation.
[COMMAND_EXECUTION]: The skill uses specific, domain-appropriate tools for database queries (e.g., LipidMaps_search_by_name, KEGG_get_pathway_genes). These tools are used as intended for information retrieval within the lipidomics domain and do not expose the system to arbitrary shell execution.
[EXTERNAL_DOWNLOADS]: The skill references established, well-known biological databases and APIs (LIPID MAPS, HMDB, KEGG, PubChem). These are trusted scientific resources and do not constitute a security risk for remote code execution or data exfiltration.

tooluniverse-lipidomics